{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 3079,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.1505376344086024e-05,
      "loss": 3.0025,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.301075268817205e-05,
      "loss": 3.0823,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.451612903225807e-05,
      "loss": 2.9825,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.60215053763441e-05,
      "loss": 2.9615,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00010752688172043011,
      "loss": 3.0319,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012903225806451613,
      "loss": 3.0456,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00015053763440860216,
      "loss": 2.9875,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001720430107526882,
      "loss": 3.0439,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001935483870967742,
      "loss": 2.9133,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00021505376344086021,
      "loss": 2.9772,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00023655913978494624,
      "loss": 2.9256,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00025806451612903227,
      "loss": 2.9884,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00027956989247311827,
      "loss": 2.8851,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0003010752688172043,
      "loss": 2.9326,
      "step": 14
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0003225806451612903,
      "loss": 2.9037,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003440860215053764,
      "loss": 2.8716,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003655913978494624,
      "loss": 2.8873,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003870967741935484,
      "loss": 2.9048,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00040860215053763443,
      "loss": 2.7661,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00043010752688172043,
      "loss": 2.7424,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00045161290322580643,
      "loss": 2.7219,
      "step": 21
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004731182795698925,
      "loss": 2.7913,
      "step": 22
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004946236559139785,
      "loss": 2.7095,
      "step": 23
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005161290322580645,
      "loss": 2.7516,
      "step": 24
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005376344086021505,
      "loss": 2.7181,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005591397849462365,
      "loss": 2.5637,
      "step": 26
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005806451612903226,
      "loss": 2.6443,
      "step": 27
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006021505376344086,
      "loss": 2.6627,
      "step": 28
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006236559139784946,
      "loss": 2.6059,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006451612903225806,
      "loss": 2.5745,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006666666666666666,
      "loss": 2.4728,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006881720430107528,
      "loss": 2.54,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007096774193548388,
      "loss": 2.4709,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007311827956989248,
      "loss": 2.4182,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007526881720430108,
      "loss": 2.409,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007741935483870968,
      "loss": 2.4798,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007956989247311828,
      "loss": 2.2774,
      "step": 37
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0008172043010752689,
      "loss": 2.3242,
      "step": 38
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0008387096774193549,
      "loss": 2.4111,
      "step": 39
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0008602150537634409,
      "loss": 2.3048,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0008817204301075269,
      "loss": 2.3662,
      "step": 41
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0009032258064516129,
      "loss": 2.3347,
      "step": 42
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0009247311827956989,
      "loss": 2.2308,
      "step": 43
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000946236559139785,
      "loss": 2.2967,
      "step": 44
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000967741935483871,
      "loss": 2.3626,
      "step": 45
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000989247311827957,
      "loss": 2.2981,
      "step": 46
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.001010752688172043,
      "loss": 2.3351,
      "step": 47
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.001032258064516129,
      "loss": 2.2606,
      "step": 48
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.001053763440860215,
      "loss": 2.2589,
      "step": 49
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.001075268817204301,
      "loss": 2.2418,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.001096774193548387,
      "loss": 2.1605,
      "step": 51
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.001118279569892473,
      "loss": 2.238,
      "step": 52
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0011397849462365592,
      "loss": 2.2403,
      "step": 53
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0011612903225806453,
      "loss": 2.2488,
      "step": 54
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0011827956989247312,
      "loss": 2.1954,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0012043010752688173,
      "loss": 2.1484,
      "step": 56
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0012258064516129032,
      "loss": 2.252,
      "step": 57
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0012473118279569893,
      "loss": 2.1787,
      "step": 58
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0012688172043010752,
      "loss": 2.1972,
      "step": 59
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0012903225806451613,
      "loss": 2.2227,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0013118279569892472,
      "loss": 2.2323,
      "step": 61
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0013333333333333333,
      "loss": 2.1606,
      "step": 62
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0013548387096774194,
      "loss": 2.2158,
      "step": 63
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0013763440860215055,
      "loss": 2.2307,
      "step": 64
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0013978494623655916,
      "loss": 2.1308,
      "step": 65
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0014193548387096775,
      "loss": 2.194,
      "step": 66
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0014408602150537636,
      "loss": 2.168,
      "step": 67
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0014623655913978495,
      "loss": 2.104,
      "step": 68
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0014838709677419356,
      "loss": 2.1663,
      "step": 69
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0015053763440860215,
      "loss": 2.1705,
      "step": 70
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0015268817204301076,
      "loss": 2.1728,
      "step": 71
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0015483870967741935,
      "loss": 2.1167,
      "step": 72
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0015698924731182796,
      "loss": 2.1928,
      "step": 73
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0015913978494623655,
      "loss": 2.1517,
      "step": 74
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0016129032258064516,
      "loss": 2.1611,
      "step": 75
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0016344086021505377,
      "loss": 2.0837,
      "step": 76
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0016559139784946238,
      "loss": 2.0847,
      "step": 77
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0016774193548387097,
      "loss": 2.0815,
      "step": 78
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0016989247311827958,
      "loss": 2.0861,
      "step": 79
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0017204301075268817,
      "loss": 2.1896,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0017419354838709678,
      "loss": 2.1261,
      "step": 81
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0017634408602150537,
      "loss": 2.1223,
      "step": 82
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0017849462365591398,
      "loss": 2.0469,
      "step": 83
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0018064516129032257,
      "loss": 2.0909,
      "step": 84
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0018279569892473118,
      "loss": 2.1279,
      "step": 85
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0018494623655913977,
      "loss": 2.0685,
      "step": 86
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0018709677419354838,
      "loss": 2.0632,
      "step": 87
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00189247311827957,
      "loss": 2.1188,
      "step": 88
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001913978494623656,
      "loss": 2.1488,
      "step": 89
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001935483870967742,
      "loss": 2.1614,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001956989247311828,
      "loss": 2.0829,
      "step": 91
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001978494623655914,
      "loss": 2.1734,
      "step": 92
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.002,
      "loss": 2.0562,
      "step": 93
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019999994465350755,
      "loss": 2.179,
      "step": 94
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019999977861409153,
      "loss": 2.1083,
      "step": 95
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001999995018819356,
      "loss": 2.1141,
      "step": 96
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001999991144573462,
      "loss": 2.1289,
      "step": 97
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019999861634075215,
      "loss": 2.1735,
      "step": 98
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019999800753270486,
      "loss": 2.092,
      "step": 99
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019999728803387815,
      "loss": 2.0592,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019999645784506853,
      "loss": 2.0804,
      "step": 101
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019999551696719495,
      "loss": 2.1273,
      "step": 102
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019999446540129888,
      "loss": 2.129,
      "step": 103
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0019999330314854438,
      "loss": 2.1476,
      "step": 104
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001999920302102179,
      "loss": 2.0677,
      "step": 105
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001999906465877285,
      "loss": 2.2254,
      "step": 106
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001999891522826078,
      "loss": 2.0805,
      "step": 107
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019998754729650993,
      "loss": 2.128,
      "step": 108
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001999858316312114,
      "loss": 2.1241,
      "step": 109
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001999840052886114,
      "loss": 2.1237,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001999820682707315,
      "loss": 2.1126,
      "step": 111
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019998002057971588,
      "loss": 2.1263,
      "step": 112
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001999778622178312,
      "loss": 2.0781,
      "step": 113
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001999755931874666,
      "loss": 2.126,
      "step": 114
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001999732134911338,
      "loss": 2.1251,
      "step": 115
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019997072313146687,
      "loss": 2.2221,
      "step": 116
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001999681221112225,
      "loss": 2.0657,
      "step": 117
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001999654104332798,
      "loss": 2.0495,
      "step": 118
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001999625881006404,
      "loss": 2.1597,
      "step": 119
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019995965511642854,
      "loss": 2.0698,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019995661148389074,
      "loss": 2.0925,
      "step": 121
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019995345720639607,
      "loss": 2.115,
      "step": 122
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019995019228743614,
      "loss": 2.0844,
      "step": 123
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019994681673062495,
      "loss": 2.015,
      "step": 124
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001999433305396991,
      "loss": 2.0416,
      "step": 125
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001999397337185174,
      "loss": 2.0867,
      "step": 126
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019993602627106136,
      "loss": 2.0684,
      "step": 127
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019993220820143484,
      "loss": 2.086,
      "step": 128
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019992827951386427,
      "loss": 2.1396,
      "step": 129
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019992424021269832,
      "loss": 2.1644,
      "step": 130
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019992009030240826,
      "loss": 2.0832,
      "step": 131
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019991582978758776,
      "loss": 2.124,
      "step": 132
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019991145867295284,
      "loss": 2.0195,
      "step": 133
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019990697696334212,
      "loss": 2.1491,
      "step": 134
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019990238466371653,
      "loss": 2.072,
      "step": 135
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001998976817791593,
      "loss": 2.0953,
      "step": 136
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0019989286831487633,
      "loss": 2.1112,
      "step": 137
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001998879442761957,
      "loss": 2.0882,
      "step": 138
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019988290966856804,
      "loss": 2.0942,
      "step": 139
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001998777644975663,
      "loss": 2.0613,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019987250876888573,
      "loss": 2.1476,
      "step": 141
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001998671424883442,
      "loss": 2.0381,
      "step": 142
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019986166566188165,
      "loss": 2.0897,
      "step": 143
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019985607829556065,
      "loss": 2.0352,
      "step": 144
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019985038039556603,
      "loss": 2.1212,
      "step": 145
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001998445719682049,
      "loss": 2.1528,
      "step": 146
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019983865301990682,
      "loss": 2.0831,
      "step": 147
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019983262355722366,
      "loss": 2.1559,
      "step": 148
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019982648358682956,
      "loss": 2.1353,
      "step": 149
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001998202331155211,
      "loss": 2.0933,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019981387215021705,
      "loss": 2.118,
      "step": 151
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001998074006979586,
      "loss": 2.0517,
      "step": 152
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019980081876590917,
      "loss": 2.1393,
      "step": 153
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019979412636135455,
      "loss": 2.0884,
      "step": 154
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001997873234917027,
      "loss": 2.0733,
      "step": 155
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001997804101644839,
      "loss": 2.0472,
      "step": 156
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001997733863873508,
      "loss": 2.0553,
      "step": 157
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019976625216807818,
      "loss": 2.045,
      "step": 158
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001997590075145631,
      "loss": 2.0846,
      "step": 159
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019975165243482497,
      "loss": 2.0594,
      "step": 160
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019974418693700525,
      "loss": 2.1156,
      "step": 161
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019973661102936774,
      "loss": 2.078,
      "step": 162
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001997289247202985,
      "loss": 2.049,
      "step": 163
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019972112801830565,
      "loss": 2.0087,
      "step": 164
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019971322093201966,
      "loss": 2.0108,
      "step": 165
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001997052034701931,
      "loss": 1.9798,
      "step": 166
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.001996970756417007,
      "loss": 2.025,
      "step": 167
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019968883745553946,
      "loss": 2.0775,
      "step": 168
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0019968048892082843,
      "loss": 2.1539,
      "step": 169
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019967203004680888,
      "loss": 2.1089,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019966346084284415,
      "loss": 2.0814,
      "step": 171
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001996547813184198,
      "loss": 2.0793,
      "step": 172
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001996459914831434,
      "loss": 1.9996,
      "step": 173
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019963709134674474,
      "loss": 2.0676,
      "step": 174
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019962808091907557,
      "loss": 2.0625,
      "step": 175
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019961896021010984,
      "loss": 2.0999,
      "step": 176
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001996097292299436,
      "loss": 2.0801,
      "step": 177
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001996003879887948,
      "loss": 2.0613,
      "step": 178
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001995909364970036,
      "loss": 2.0745,
      "step": 179
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001995813747650321,
      "loss": 2.0409,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019957170280346446,
      "loss": 2.0792,
      "step": 181
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001995619206230069,
      "loss": 2.0212,
      "step": 182
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019955202823448764,
      "loss": 2.0337,
      "step": 183
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019954202564885677,
      "loss": 2.0714,
      "step": 184
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001995319128771865,
      "loss": 2.0505,
      "step": 185
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019952168993067096,
      "loss": 2.0501,
      "step": 186
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001995113568206262,
      "loss": 2.0334,
      "step": 187
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001995009135584903,
      "loss": 2.1424,
      "step": 188
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019949036015582317,
      "loss": 2.1002,
      "step": 189
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019947969662430674,
      "loss": 2.096,
      "step": 190
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019946892297574475,
      "loss": 2.0934,
      "step": 191
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001994580392220629,
      "loss": 2.1075,
      "step": 192
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019944704537530867,
      "loss": 2.1223,
      "step": 193
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001994359414476516,
      "loss": 2.0245,
      "step": 194
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019942472745138285,
      "loss": 2.0902,
      "step": 195
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001994134033989156,
      "loss": 2.129,
      "step": 196
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001994019693027847,
      "loss": 2.0232,
      "step": 197
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00199390425175647,
      "loss": 2.0766,
      "step": 198
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0019937877103028095,
      "loss": 2.0884,
      "step": 199
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001993670068795869,
      "loss": 2.0765,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019935513273658697,
      "loss": 2.0611,
      "step": 201
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019934314861442494,
      "loss": 2.0507,
      "step": 202
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.001993310545263665,
      "loss": 2.0921,
      "step": 203
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019931885048579882,
      "loss": 2.0731,
      "step": 204
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00199306536506231,
      "loss": 2.0434,
      "step": 205
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.001992941126012937,
      "loss": 2.1057,
      "step": 206
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.001992815787847394,
      "loss": 2.0512,
      "step": 207
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.001992689350704421,
      "loss": 2.1049,
      "step": 208
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.001992561814723975,
      "loss": 2.0961,
      "step": 209
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.001992433180047229,
      "loss": 2.0657,
      "step": 210
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019923034468165733,
      "loss": 2.1074,
      "step": 211
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.001992172615175613,
      "loss": 2.0553,
      "step": 212
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00199204068526917,
      "loss": 2.0443,
      "step": 213
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019919076572432813,
      "loss": 2.0007,
      "step": 214
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019917735312451994,
      "loss": 2.1088,
      "step": 215
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019916383074233927,
      "loss": 2.0499,
      "step": 216
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019915019859275437,
      "loss": 2.0655,
      "step": 217
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019913645669085516,
      "loss": 2.1092,
      "step": 218
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.001991226050518529,
      "loss": 2.0206,
      "step": 219
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019910864369108044,
      "loss": 2.1384,
      "step": 220
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00199094572623992,
      "loss": 2.077,
      "step": 221
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019908039186616326,
      "loss": 2.0799,
      "step": 222
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019906610143329132,
      "loss": 2.037,
      "step": 223
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019905170134119467,
      "loss": 2.1598,
      "step": 224
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019903719160581325,
      "loss": 2.0714,
      "step": 225
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019902257224320833,
      "loss": 2.0904,
      "step": 226
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019900784326956243,
      "loss": 2.103,
      "step": 227
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019899300470117955,
      "loss": 2.0663,
      "step": 228
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019897805655448497,
      "loss": 2.0921,
      "step": 229
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0019896299884602517,
      "loss": 2.1032,
      "step": 230
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019894783159246803,
      "loss": 2.1365,
      "step": 231
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001989325548106026,
      "loss": 2.0476,
      "step": 232
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019891716851733925,
      "loss": 2.0533,
      "step": 233
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001989016727297095,
      "loss": 2.0276,
      "step": 234
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019888606746486614,
      "loss": 2.1047,
      "step": 235
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00198870352740083,
      "loss": 2.0429,
      "step": 236
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001988545285727553,
      "loss": 2.0694,
      "step": 237
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001988385949803992,
      "loss": 2.0591,
      "step": 238
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001988225519806521,
      "loss": 2.0747,
      "step": 239
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019880639959127247,
      "loss": 2.0278,
      "step": 240
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019879013783013987,
      "loss": 2.0023,
      "step": 241
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001987737667152549,
      "loss": 2.0752,
      "step": 242
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019875728626473936,
      "loss": 2.0716,
      "step": 243
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001987406964968358,
      "loss": 1.969,
      "step": 244
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00198723997429908,
      "loss": 2.0557,
      "step": 245
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019870718908244064,
      "loss": 2.0906,
      "step": 246
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001986902714730394,
      "loss": 2.1311,
      "step": 247
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019867324462043085,
      "loss": 2.0179,
      "step": 248
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019865610854346255,
      "loss": 2.0583,
      "step": 249
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019863886326110295,
      "loss": 2.0916,
      "step": 250
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001986215087924414,
      "loss": 2.2303,
      "step": 251
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019860404515668795,
      "loss": 2.081,
      "step": 252
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019858647237317372,
      "loss": 2.0494,
      "step": 253
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001985687904613505,
      "loss": 2.0448,
      "step": 254
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00198550999440791,
      "loss": 2.0633,
      "step": 255
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019853309933118854,
      "loss": 2.0759,
      "step": 256
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019851509015235734,
      "loss": 2.0599,
      "step": 257
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019849697192423233,
      "loss": 2.0558,
      "step": 258
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0019847874466686903,
      "loss": 2.0938,
      "step": 259
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001984604084004438,
      "loss": 1.9067,
      "step": 260
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.001984419631452536,
      "loss": 2.0445,
      "step": 261
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00198423408921716,
      "loss": 2.162,
      "step": 262
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001984047457503692,
      "loss": 2.1467,
      "step": 263
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001983859736518721,
      "loss": 2.1907,
      "step": 264
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019836709264700403,
      "loss": 2.0638,
      "step": 265
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019834810275666495,
      "loss": 2.1193,
      "step": 266
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019832900400187543,
      "loss": 2.3763,
      "step": 267
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001983097964037763,
      "loss": 2.2975,
      "step": 268
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001982904799836291,
      "loss": 2.302,
      "step": 269
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001982710547628158,
      "loss": 2.2486,
      "step": 270
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019825152076283865,
      "loss": 2.3138,
      "step": 271
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001982318780053205,
      "loss": 2.2677,
      "step": 272
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019821212651200443,
      "loss": 2.4078,
      "step": 273
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019819226630475406,
      "loss": 2.4565,
      "step": 274
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001981722974055532,
      "loss": 2.6142,
      "step": 275
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019815221983650595,
      "loss": 2.6623,
      "step": 276
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019813203361983686,
      "loss": 2.6342,
      "step": 277
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019811173877789063,
      "loss": 2.6934,
      "step": 278
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001980913353331322,
      "loss": 2.666,
      "step": 279
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001980708233081468,
      "loss": 2.6922,
      "step": 280
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001980502027256398,
      "loss": 2.6918,
      "step": 281
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019802947360843667,
      "loss": 2.6234,
      "step": 282
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019800863597948313,
      "loss": 2.6921,
      "step": 283
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019798768986184503,
      "loss": 2.565,
      "step": 284
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001979666352787082,
      "loss": 2.6179,
      "step": 285
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019794547225337853,
      "loss": 2.6638,
      "step": 286
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001979242008092821,
      "loss": 2.6022,
      "step": 287
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001979028209699649,
      "loss": 2.6106,
      "step": 288
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001978813327590928,
      "loss": 2.5023,
      "step": 289
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019785973620045187,
      "loss": 2.6142,
      "step": 290
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019783803131794794,
      "loss": 2.5806,
      "step": 291
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0019781621813560676,
      "loss": 2.5048,
      "step": 292
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001977942966775741,
      "loss": 2.5324,
      "step": 293
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019777226696811533,
      "loss": 2.5818,
      "step": 294
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019775012903161587,
      "loss": 2.5093,
      "step": 295
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001977278828925809,
      "loss": 2.5315,
      "step": 296
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019770552857563523,
      "loss": 2.4867,
      "step": 297
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001976830661055236,
      "loss": 2.436,
      "step": 298
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019766049550711037,
      "loss": 2.468,
      "step": 299
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001976378168053796,
      "loss": 2.416,
      "step": 300
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019761503002543508,
      "loss": 2.4602,
      "step": 301
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019759213519250007,
      "loss": 2.4497,
      "step": 302
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019756913233191765,
      "loss": 2.4976,
      "step": 303
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001975460214691503,
      "loss": 2.4928,
      "step": 304
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019752280262978015,
      "loss": 2.4358,
      "step": 305
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019749947583950884,
      "loss": 2.4631,
      "step": 306
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019747604112415745,
      "loss": 2.445,
      "step": 307
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019745249850966658,
      "loss": 2.4122,
      "step": 308
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001974288480220963,
      "loss": 2.4289,
      "step": 309
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019740508968762597,
      "loss": 2.4031,
      "step": 310
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019738122353255443,
      "loss": 2.4523,
      "step": 311
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001973572495832999,
      "loss": 2.4728,
      "step": 312
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019733316786639974,
      "loss": 2.4023,
      "step": 313
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019730897840851084,
      "loss": 2.4529,
      "step": 314
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019728468123640917,
      "loss": 2.4618,
      "step": 315
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019726027637698997,
      "loss": 2.4451,
      "step": 316
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019723576385726775,
      "loss": 2.471,
      "step": 317
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019721114370437613,
      "loss": 2.4193,
      "step": 318
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019718641594556794,
      "loss": 2.4481,
      "step": 319
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019716158060821497,
      "loss": 2.432,
      "step": 320
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001971366377198083,
      "loss": 2.3644,
      "step": 321
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019711158730795794,
      "loss": 2.4362,
      "step": 322
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0019708642940039294,
      "loss": 2.3846,
      "step": 323
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019706116402496126,
      "loss": 2.3606,
      "step": 324
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019703579120963,
      "loss": 2.3842,
      "step": 325
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00197010310982485,
      "loss": 2.4227,
      "step": 326
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019698472337173114,
      "loss": 2.4753,
      "step": 327
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001969590284056921,
      "loss": 2.5037,
      "step": 328
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019693322611281042,
      "loss": 2.3915,
      "step": 329
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019690731652164738,
      "loss": 2.4047,
      "step": 330
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019688129966088314,
      "loss": 2.4123,
      "step": 331
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019685517555931647,
      "loss": 2.438,
      "step": 332
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00196828944245865,
      "loss": 2.3101,
      "step": 333
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019680260574956488,
      "loss": 2.3534,
      "step": 334
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00196776160099571,
      "loss": 2.3386,
      "step": 335
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001967496073251569,
      "loss": 2.2228,
      "step": 336
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019672294745571453,
      "loss": 2.3746,
      "step": 337
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019669618052075457,
      "loss": 2.3131,
      "step": 338
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019666930654990613,
      "loss": 2.2764,
      "step": 339
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001966423255729168,
      "loss": 2.3374,
      "step": 340
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019661523761965263,
      "loss": 2.2712,
      "step": 341
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001965880427200981,
      "loss": 2.2847,
      "step": 342
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019656074090435597,
      "loss": 2.3434,
      "step": 343
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001965333322026476,
      "loss": 2.3203,
      "step": 344
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019650581664531234,
      "loss": 2.1935,
      "step": 345
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019647819426280807,
      "loss": 2.2213,
      "step": 346
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001964504650857108,
      "loss": 2.2762,
      "step": 347
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.001964226291447148,
      "loss": 2.2515,
      "step": 348
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019639468647063246,
      "loss": 2.2773,
      "step": 349
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019636663709439446,
      "loss": 2.3161,
      "step": 350
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019633848104704935,
      "loss": 2.2455,
      "step": 351
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019631021835976406,
      "loss": 2.236,
      "step": 352
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019628184906382326,
      "loss": 2.2653,
      "step": 353
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0019625337319062984,
      "loss": 2.3332,
      "step": 354
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019622479077170455,
      "loss": 2.3303,
      "step": 355
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001961961018386862,
      "loss": 2.2416,
      "step": 356
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019616730642333137,
      "loss": 2.2743,
      "step": 357
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019613840455751457,
      "loss": 2.3369,
      "step": 358
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019610939627322816,
      "loss": 2.2322,
      "step": 359
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001960802816025822,
      "loss": 2.2351,
      "step": 360
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019605106057780475,
      "loss": 2.1948,
      "step": 361
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019602173323124126,
      "loss": 2.2395,
      "step": 362
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001959922995953551,
      "loss": 2.2546,
      "step": 363
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019596275970272733,
      "loss": 2.1739,
      "step": 364
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001959331135860564,
      "loss": 2.2841,
      "step": 365
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019590336127815857,
      "loss": 2.2876,
      "step": 366
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019587350281196755,
      "loss": 2.2651,
      "step": 367
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001958435382205345,
      "loss": 2.2302,
      "step": 368
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019581346753702825,
      "loss": 2.198,
      "step": 369
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019578329079473484,
      "loss": 2.2241,
      "step": 370
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001957530080270578,
      "loss": 2.2068,
      "step": 371
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019572261926751808,
      "loss": 2.3018,
      "step": 372
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001956921245497539,
      "loss": 2.2838,
      "step": 373
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001956615239075207,
      "loss": 2.2613,
      "step": 374
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019563081737469135,
      "loss": 2.1727,
      "step": 375
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019560000498525573,
      "loss": 2.28,
      "step": 376
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019556908677332108,
      "loss": 2.1828,
      "step": 377
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019553806277311163,
      "loss": 2.1922,
      "step": 378
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001955069330189688,
      "loss": 2.153,
      "step": 379
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019547569754535103,
      "loss": 2.2754,
      "step": 380
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001954443563868338,
      "loss": 2.2508,
      "step": 381
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001954129095781096,
      "loss": 2.2654,
      "step": 382
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019538135715398783,
      "loss": 2.2628,
      "step": 383
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0019534969914939476,
      "loss": 2.2951,
      "step": 384
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001953179355993737,
      "loss": 2.2696,
      "step": 385
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019528606653908451,
      "loss": 2.2702,
      "step": 386
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019525409200380412,
      "loss": 2.245,
      "step": 387
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019522201202892607,
      "loss": 2.2476,
      "step": 388
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019518982664996063,
      "loss": 2.2282,
      "step": 389
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019515753590253477,
      "loss": 2.2384,
      "step": 390
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019512513982239206,
      "loss": 2.1096,
      "step": 391
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019509263844539274,
      "loss": 2.2024,
      "step": 392
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019506003180751348,
      "loss": 2.203,
      "step": 393
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001950273199448476,
      "loss": 2.244,
      "step": 394
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001949945028936048,
      "loss": 2.2105,
      "step": 395
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019496158069011128,
      "loss": 2.2775,
      "step": 396
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019492855337080962,
      "loss": 2.2232,
      "step": 397
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019489542097225869,
      "loss": 2.2179,
      "step": 398
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019486218353113377,
      "loss": 2.2082,
      "step": 399
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001948288410842264,
      "loss": 2.259,
      "step": 400
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019479539366844426,
      "loss": 2.2092,
      "step": 401
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019476184132081137,
      "loss": 2.2653,
      "step": 402
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019472818407846777,
      "loss": 2.2636,
      "step": 403
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019469442197866966,
      "loss": 2.2524,
      "step": 404
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001946605550587894,
      "loss": 2.2221,
      "step": 405
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001946265833563152,
      "loss": 2.1822,
      "step": 406
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001945925069088514,
      "loss": 2.1763,
      "step": 407
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019455832575411823,
      "loss": 2.2288,
      "step": 408
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001945240399299518,
      "loss": 2.1712,
      "step": 409
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019448964947430415,
      "loss": 2.2069,
      "step": 410
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019445515442524308,
      "loss": 2.1561,
      "step": 411
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001944205548209522,
      "loss": 2.1803,
      "step": 412
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019438585069973086,
      "loss": 2.1821,
      "step": 413
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0019435104209999405,
      "loss": 2.1603,
      "step": 414
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001943161290602725,
      "loss": 2.1016,
      "step": 415
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019428111161921243,
      "loss": 2.1675,
      "step": 416
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019424598981557573,
      "loss": 2.2184,
      "step": 417
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001942107636882398,
      "loss": 2.1275,
      "step": 418
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019417543327619742,
      "loss": 2.1577,
      "step": 419
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019413999861855693,
      "loss": 2.1846,
      "step": 420
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00194104459754542,
      "loss": 2.1391,
      "step": 421
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019406881672349165,
      "loss": 2.1704,
      "step": 422
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019403306956486024,
      "loss": 2.1646,
      "step": 423
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019399721831821735,
      "loss": 2.1891,
      "step": 424
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019396126302324776,
      "loss": 2.1448,
      "step": 425
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019392520371975153,
      "loss": 2.1243,
      "step": 426
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019388904044764373,
      "loss": 2.2401,
      "step": 427
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019385277324695455,
      "loss": 2.1384,
      "step": 428
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001938164021578293,
      "loss": 2.1652,
      "step": 429
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001937799272205282,
      "loss": 2.0959,
      "step": 430
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001937433484754264,
      "loss": 2.0891,
      "step": 431
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019370666596301405,
      "loss": 2.1236,
      "step": 432
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019366987972389614,
      "loss": 2.2146,
      "step": 433
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001936329897987924,
      "loss": 2.154,
      "step": 434
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019359599622853741,
      "loss": 2.1548,
      "step": 435
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019355889905408046,
      "loss": 2.1639,
      "step": 436
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.001935216983164855,
      "loss": 2.0704,
      "step": 437
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019348439405693122,
      "loss": 2.1747,
      "step": 438
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019344698631671069,
      "loss": 2.1035,
      "step": 439
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019340947513723178,
      "loss": 2.1711,
      "step": 440
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019337186056001662,
      "loss": 2.1059,
      "step": 441
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019333414262670198,
      "loss": 2.1624,
      "step": 442
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019329632137903895,
      "loss": 2.1371,
      "step": 443
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00193258396858893,
      "loss": 2.1443,
      "step": 444
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019322036910824393,
      "loss": 2.1459,
      "step": 445
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0019318223816918575,
      "loss": 2.1783,
      "step": 446
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019314400408392675,
      "loss": 2.1633,
      "step": 447
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019310566689478938,
      "loss": 2.1449,
      "step": 448
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019306722664421026,
      "loss": 2.0984,
      "step": 449
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019302868337474,
      "loss": 2.1321,
      "step": 450
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001929900371290433,
      "loss": 2.15,
      "step": 451
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019295128794989886,
      "loss": 2.2113,
      "step": 452
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019291243588019933,
      "loss": 2.1699,
      "step": 453
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019287348096295117,
      "loss": 2.1483,
      "step": 454
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019283442324127477,
      "loss": 2.1784,
      "step": 455
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019279526275840428,
      "loss": 2.1405,
      "step": 456
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001927559995576876,
      "loss": 2.1672,
      "step": 457
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019271663368258635,
      "loss": 2.1635,
      "step": 458
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001926771651766758,
      "loss": 2.1517,
      "step": 459
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019263759408364482,
      "loss": 2.1726,
      "step": 460
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001925979204472958,
      "loss": 2.1924,
      "step": 461
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001925581443115447,
      "loss": 2.0985,
      "step": 462
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019251826572042093,
      "loss": 2.0917,
      "step": 463
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019247828471806723,
      "loss": 2.1681,
      "step": 464
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019243820134873984,
      "loss": 2.1743,
      "step": 465
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001923980156568082,
      "loss": 2.0513,
      "step": 466
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00192357727686755,
      "loss": 2.117,
      "step": 467
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001923173374831763,
      "loss": 2.1436,
      "step": 468
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019227684509078116,
      "loss": 2.177,
      "step": 469
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019223625055439185,
      "loss": 2.1096,
      "step": 470
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019219555391894363,
      "loss": 2.1981,
      "step": 471
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019215475522948485,
      "loss": 2.1588,
      "step": 472
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001921138545311768,
      "loss": 2.2012,
      "step": 473
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019207285186929367,
      "loss": 2.1444,
      "step": 474
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019203174728922253,
      "loss": 2.1795,
      "step": 475
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0019199054083646329,
      "loss": 2.1323,
      "step": 476
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001919492325566286,
      "loss": 2.1902,
      "step": 477
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019190782249544375,
      "loss": 2.1342,
      "step": 478
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001918663106987469,
      "loss": 2.2216,
      "step": 479
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001918246972124886,
      "loss": 2.1363,
      "step": 480
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001917829820827321,
      "loss": 2.0614,
      "step": 481
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001917411653556531,
      "loss": 2.1501,
      "step": 482
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019169924707753982,
      "loss": 2.128,
      "step": 483
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019165722729479284,
      "loss": 2.1603,
      "step": 484
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019161510605392512,
      "loss": 2.079,
      "step": 485
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019157288340156185,
      "loss": 2.0859,
      "step": 486
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019153055938444061,
      "loss": 2.1403,
      "step": 487
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019148813404941114,
      "loss": 2.0705,
      "step": 488
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019144560744343525,
      "loss": 2.1252,
      "step": 489
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019140297961358693,
      "loss": 2.1532,
      "step": 490
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001913602506070522,
      "loss": 2.1791,
      "step": 491
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019131742047112908,
      "loss": 2.1478,
      "step": 492
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019127448925322752,
      "loss": 2.1109,
      "step": 493
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019123145700086935,
      "loss": 2.191,
      "step": 494
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001911883237616883,
      "loss": 2.1955,
      "step": 495
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019114508958342977,
      "loss": 2.1231,
      "step": 496
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019110175451395107,
      "loss": 2.1253,
      "step": 497
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019105831860122095,
      "loss": 2.1387,
      "step": 498
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019101478189332002,
      "loss": 2.1932,
      "step": 499
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019097114443844033,
      "loss": 2.1489,
      "step": 500
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019092740628488545,
      "loss": 2.1627,
      "step": 501
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019088356748107047,
      "loss": 2.0619,
      "step": 502
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001908396280755219,
      "loss": 2.1345,
      "step": 503
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019079558811687751,
      "loss": 2.1053,
      "step": 504
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019075144765388654,
      "loss": 2.1282,
      "step": 505
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019070720673540933,
      "loss": 2.1785,
      "step": 506
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019066286541041743,
      "loss": 2.1153,
      "step": 507
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0019061842372799368,
      "loss": 2.0267,
      "step": 508
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019057388173733183,
      "loss": 2.1919,
      "step": 509
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019052923948773674,
      "loss": 2.1288,
      "step": 510
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019048449702862428,
      "loss": 2.1042,
      "step": 511
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019043965440952123,
      "loss": 2.1246,
      "step": 512
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019039471168006514,
      "loss": 2.0712,
      "step": 513
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019034966889000455,
      "loss": 2.1907,
      "step": 514
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019030452608919859,
      "loss": 2.1392,
      "step": 515
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019025928332761727,
      "loss": 2.1789,
      "step": 516
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019021394065534105,
      "loss": 2.126,
      "step": 517
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019016849812256117,
      "loss": 2.1303,
      "step": 518
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019012295577957928,
      "loss": 2.1111,
      "step": 519
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019007731367680755,
      "loss": 2.2,
      "step": 520
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0019003157186476864,
      "loss": 2.0795,
      "step": 521
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018998573039409547,
      "loss": 2.1403,
      "step": 522
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018993978931553137,
      "loss": 2.0947,
      "step": 523
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018989374867992986,
      "loss": 2.0896,
      "step": 524
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018984760853825472,
      "loss": 2.123,
      "step": 525
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018980136894157984,
      "loss": 2.0766,
      "step": 526
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001897550299410892,
      "loss": 2.1781,
      "step": 527
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018970859158807685,
      "loss": 2.0749,
      "step": 528
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018966205393394677,
      "loss": 1.9679,
      "step": 529
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018961541703021287,
      "loss": 2.0662,
      "step": 530
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018956868092849894,
      "loss": 2.0647,
      "step": 531
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018952184568053858,
      "loss": 2.1379,
      "step": 532
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001894749113381751,
      "loss": 2.116,
      "step": 533
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018942787795336153,
      "loss": 1.9847,
      "step": 534
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018938074557816056,
      "loss": 2.1033,
      "step": 535
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018933351426474439,
      "loss": 2.0621,
      "step": 536
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0018928618406539477,
      "loss": 2.1301,
      "step": 537
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.001892387550325029,
      "loss": 2.0771,
      "step": 538
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018919122721856943,
      "loss": 2.0607,
      "step": 539
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001891436006762043,
      "loss": 1.9934,
      "step": 540
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018909587545812671,
      "loss": 2.1134,
      "step": 541
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018904805161716522,
      "loss": 2.1036,
      "step": 542
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018900012920625737,
      "loss": 2.1144,
      "step": 543
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018895210827844997,
      "loss": 2.0211,
      "step": 544
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018890398888689879,
      "loss": 2.0266,
      "step": 545
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018885577108486862,
      "loss": 2.0803,
      "step": 546
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018880745492573321,
      "loss": 2.0821,
      "step": 547
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018875904046297513,
      "loss": 2.178,
      "step": 548
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018871052775018581,
      "loss": 2.0534,
      "step": 549
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001886619168410654,
      "loss": 2.0869,
      "step": 550
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018861320778942282,
      "loss": 2.0644,
      "step": 551
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001885644006491755,
      "loss": 2.1137,
      "step": 552
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018851549547434958,
      "loss": 2.0914,
      "step": 553
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018846649231907962,
      "loss": 1.9875,
      "step": 554
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018841739123760868,
      "loss": 2.1565,
      "step": 555
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018836819228428823,
      "loss": 2.1218,
      "step": 556
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018831889551357804,
      "loss": 2.0831,
      "step": 557
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001882695009800462,
      "loss": 2.1312,
      "step": 558
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018822000873836898,
      "loss": 2.0955,
      "step": 559
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018817041884333081,
      "loss": 2.095,
      "step": 560
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018812073134982425,
      "loss": 2.1001,
      "step": 561
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018807094631284986,
      "loss": 2.036,
      "step": 562
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018802106378751615,
      "loss": 2.0238,
      "step": 563
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018797108382903964,
      "loss": 2.122,
      "step": 564
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018792100649274457,
      "loss": 2.0612,
      "step": 565
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001878708318340631,
      "loss": 2.0584,
      "step": 566
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00187820559908535,
      "loss": 2.1101,
      "step": 567
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018777019077180783,
      "loss": 2.0248,
      "step": 568
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0018771972447963665,
      "loss": 2.0237,
      "step": 569
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001876691610878841,
      "loss": 2.0771,
      "step": 570
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018761850065252032,
      "loss": 2.0118,
      "step": 571
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018756774322962282,
      "loss": 2.1014,
      "step": 572
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018751688887537657,
      "loss": 2.1533,
      "step": 573
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018746593764607377,
      "loss": 2.0737,
      "step": 574
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001874148895981138,
      "loss": 2.0823,
      "step": 575
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001873637447880033,
      "loss": 2.1064,
      "step": 576
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018731250327235598,
      "loss": 2.061,
      "step": 577
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018726116510789264,
      "loss": 1.9748,
      "step": 578
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018720973035144099,
      "loss": 2.0707,
      "step": 579
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018715819905993566,
      "loss": 2.1104,
      "step": 580
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018710657129041826,
      "loss": 1.9724,
      "step": 581
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018705484710003705,
      "loss": 2.0259,
      "step": 582
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001870030265460471,
      "loss": 2.1052,
      "step": 583
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018695110968581013,
      "loss": 2.135,
      "step": 584
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018689909657679444,
      "loss": 2.0598,
      "step": 585
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018684698727657494,
      "loss": 2.0408,
      "step": 586
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018679478184283292,
      "loss": 2.0174,
      "step": 587
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018674248033335617,
      "loss": 2.0058,
      "step": 588
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018669008280603877,
      "loss": 2.0425,
      "step": 589
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001866375893188811,
      "loss": 2.114,
      "step": 590
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018658499992998978,
      "loss": 2.0742,
      "step": 591
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018653231469757756,
      "loss": 1.9674,
      "step": 592
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018647953367996336,
      "loss": 2.0053,
      "step": 593
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018642665693557197,
      "loss": 2.1688,
      "step": 594
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018637368452293428,
      "loss": 2.0674,
      "step": 595
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018632061650068709,
      "loss": 2.0846,
      "step": 596
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018626745292757286,
      "loss": 2.0896,
      "step": 597
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018621419386244003,
      "loss": 1.9572,
      "step": 598
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0018616083936424262,
      "loss": 2.1027,
      "step": 599
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001861073894920403,
      "loss": 2.0241,
      "step": 600
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018605384430499833,
      "loss": 2.0724,
      "step": 601
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018600020386238753,
      "loss": 1.9851,
      "step": 602
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018594646822358402,
      "loss": 2.0904,
      "step": 603
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018589263744806948,
      "loss": 2.0285,
      "step": 604
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018583871159543071,
      "loss": 1.9982,
      "step": 605
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001857846907253599,
      "loss": 2.0522,
      "step": 606
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018573057489765436,
      "loss": 2.0341,
      "step": 607
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018567636417221652,
      "loss": 2.0398,
      "step": 608
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018562205860905379,
      "loss": 2.1015,
      "step": 609
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018556765826827871,
      "loss": 2.0336,
      "step": 610
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018551316321010858,
      "loss": 2.0453,
      "step": 611
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018545857349486564,
      "loss": 2.1177,
      "step": 612
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018540388918297681,
      "loss": 2.0428,
      "step": 613
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018534911033497386,
      "loss": 2.04,
      "step": 614
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018529423701149313,
      "loss": 2.089,
      "step": 615
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018523926927327549,
      "loss": 2.0528,
      "step": 616
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001851842071811664,
      "loss": 2.1072,
      "step": 617
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018512905079611573,
      "loss": 2.1288,
      "step": 618
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018507380017917772,
      "loss": 2.0465,
      "step": 619
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018501845539151097,
      "loss": 2.0475,
      "step": 620
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001849630164943782,
      "loss": 2.0834,
      "step": 621
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018490748354914647,
      "loss": 2.0578,
      "step": 622
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018485185661728677,
      "loss": 2.0583,
      "step": 623
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018479613576037426,
      "loss": 2.0998,
      "step": 624
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00184740321040088,
      "loss": 2.0542,
      "step": 625
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00184684412518211,
      "loss": 2.0458,
      "step": 626
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018462841025663002,
      "loss": 2.0536,
      "step": 627
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001845723143173357,
      "loss": 1.9684,
      "step": 628
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018451612476242225,
      "loss": 2.0439,
      "step": 629
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.001844598416540876,
      "loss": 2.0858,
      "step": 630
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0018440346505463321,
      "loss": 2.0949,
      "step": 631
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018434699502646397,
      "loss": 2.0807,
      "step": 632
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001842904316320883,
      "loss": 2.1028,
      "step": 633
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018423377493411788,
      "loss": 2.1203,
      "step": 634
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001841770249952677,
      "loss": 2.0576,
      "step": 635
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018412018187835596,
      "loss": 2.0445,
      "step": 636
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018406324564630401,
      "loss": 2.0403,
      "step": 637
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018400621636213625,
      "loss": 2.0406,
      "step": 638
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018394909408898012,
      "loss": 2.075,
      "step": 639
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018389187889006596,
      "loss": 2.0461,
      "step": 640
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018383457082872699,
      "loss": 2.1189,
      "step": 641
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001837771699683992,
      "loss": 2.0012,
      "step": 642
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001837196763726213,
      "loss": 2.0922,
      "step": 643
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001836620901050347,
      "loss": 2.0066,
      "step": 644
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018360441122938333,
      "loss": 2.027,
      "step": 645
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001835466398095137,
      "loss": 1.9155,
      "step": 646
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018348877590937467,
      "loss": 2.0399,
      "step": 647
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018343081959301757,
      "loss": 2.1007,
      "step": 648
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018337277092459591,
      "loss": 2.0416,
      "step": 649
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018331462996836554,
      "loss": 2.0681,
      "step": 650
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018325639678868444,
      "loss": 2.0375,
      "step": 651
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001831980714500126,
      "loss": 2.0371,
      "step": 652
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018313965401691213,
      "loss": 2.1078,
      "step": 653
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018308114455404696,
      "loss": 2.0314,
      "step": 654
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018302254312618303,
      "loss": 2.0954,
      "step": 655
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018296384979818799,
      "loss": 2.0807,
      "step": 656
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018290506463503125,
      "loss": 2.0138,
      "step": 657
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018284618770178383,
      "loss": 2.0349,
      "step": 658
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018278721906361834,
      "loss": 2.0406,
      "step": 659
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018272815878580902,
      "loss": 2.0662,
      "step": 660
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0018266900693373138,
      "loss": 2.0533,
      "step": 661
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018260976357286239,
      "loss": 2.0415,
      "step": 662
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018255042876878028,
      "loss": 2.0553,
      "step": 663
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018249100258716454,
      "loss": 2.0603,
      "step": 664
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018243148509379577,
      "loss": 2.0532,
      "step": 665
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018237187635455566,
      "loss": 2.048,
      "step": 666
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018231217643542691,
      "loss": 2.0076,
      "step": 667
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018225238540249317,
      "loss": 2.0231,
      "step": 668
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018219250332193885,
      "loss": 2.0706,
      "step": 669
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018213253026004926,
      "loss": 2.0822,
      "step": 670
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018207246628321038,
      "loss": 2.0346,
      "step": 671
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018201231145790879,
      "loss": 2.0709,
      "step": 672
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018195206585073164,
      "loss": 2.0654,
      "step": 673
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018189172952836668,
      "loss": 1.9906,
      "step": 674
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001818313025576019,
      "loss": 2.0052,
      "step": 675
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018177078500532574,
      "loss": 2.0532,
      "step": 676
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001817101769385269,
      "loss": 2.1184,
      "step": 677
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018164947842429426,
      "loss": 2.033,
      "step": 678
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001815886895298168,
      "loss": 2.0501,
      "step": 679
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001815278103223836,
      "loss": 2.0147,
      "step": 680
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001814668408693836,
      "loss": 2.0444,
      "step": 681
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018140578123830577,
      "loss": 2.1034,
      "step": 682
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018134463149673881,
      "loss": 1.9986,
      "step": 683
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001812833917123712,
      "loss": 2.0067,
      "step": 684
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001812220619529911,
      "loss": 2.0035,
      "step": 685
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018116064228648622,
      "loss": 2.0901,
      "step": 686
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018109913278084387,
      "loss": 2.0863,
      "step": 687
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001810375335041507,
      "loss": 2.0204,
      "step": 688
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001809758445245928,
      "loss": 2.0573,
      "step": 689
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001809140659104556,
      "loss": 2.1379,
      "step": 690
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018085219773012365,
      "loss": 2.0386,
      "step": 691
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0018079024005208067,
      "loss": 1.9666,
      "step": 692
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0018072819294490947,
      "loss": 2.1035,
      "step": 693
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0018066605647729188,
      "loss": 2.0549,
      "step": 694
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0018060383071800859,
      "loss": 2.0504,
      "step": 695
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0018054151573593912,
      "loss": 2.1283,
      "step": 696
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0018047911160006182,
      "loss": 2.0588,
      "step": 697
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001804166183794537,
      "loss": 2.1567,
      "step": 698
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001803540361432903,
      "loss": 2.0114,
      "step": 699
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0018029136496084583,
      "loss": 2.072,
      "step": 700
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001802286049014929,
      "loss": 2.0697,
      "step": 701
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001801657560347025,
      "loss": 2.1085,
      "step": 702
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0018010281843004385,
      "loss": 2.1032,
      "step": 703
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0018003979215718451,
      "loss": 2.096,
      "step": 704
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017997667728589014,
      "loss": 2.1098,
      "step": 705
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017991347388602447,
      "loss": 2.11,
      "step": 706
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017985018202754922,
      "loss": 1.9995,
      "step": 707
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017978680178052403,
      "loss": 1.9648,
      "step": 708
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017972333321510643,
      "loss": 2.0677,
      "step": 709
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017965977640155165,
      "loss": 2.0654,
      "step": 710
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001795961314102126,
      "loss": 2.109,
      "step": 711
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017953239831153987,
      "loss": 2.0635,
      "step": 712
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017946857717608144,
      "loss": 2.0827,
      "step": 713
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017940466807448293,
      "loss": 1.9763,
      "step": 714
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001793406710774872,
      "loss": 2.0237,
      "step": 715
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017927658625593438,
      "loss": 2.0455,
      "step": 716
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017921241368076195,
      "loss": 2.0798,
      "step": 717
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001791481534230044,
      "loss": 2.0623,
      "step": 718
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017908380555379337,
      "loss": 2.0078,
      "step": 719
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017901937014435738,
      "loss": 2.0683,
      "step": 720
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017895484726602195,
      "loss": 2.0991,
      "step": 721
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017889023699020937,
      "loss": 2.0288,
      "step": 722
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0017882553938843868,
      "loss": 2.0175,
      "step": 723
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001787607545323256,
      "loss": 2.0567,
      "step": 724
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017869588249358242,
      "loss": 2.0658,
      "step": 725
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001786309233440179,
      "loss": 2.023,
      "step": 726
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001785658771555373,
      "loss": 1.9744,
      "step": 727
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017850074400014217,
      "loss": 2.0452,
      "step": 728
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017843552394993035,
      "loss": 2.0626,
      "step": 729
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017837021707709586,
      "loss": 2.0739,
      "step": 730
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017830482345392881,
      "loss": 2.089,
      "step": 731
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001782393431528154,
      "loss": 2.0068,
      "step": 732
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017817377624623767,
      "loss": 2.1089,
      "step": 733
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017810812280677365,
      "loss": 2.0301,
      "step": 734
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017804238290709702,
      "loss": 2.1516,
      "step": 735
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017797655661997728,
      "loss": 2.0661,
      "step": 736
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017791064401827953,
      "loss": 2.1082,
      "step": 737
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017784464517496435,
      "loss": 2.0286,
      "step": 738
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017777856016308786,
      "loss": 2.0662,
      "step": 739
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017771238905580154,
      "loss": 2.086,
      "step": 740
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001776461319263521,
      "loss": 1.9633,
      "step": 741
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017757978884808164,
      "loss": 2.0705,
      "step": 742
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001775133598944272,
      "loss": 2.0439,
      "step": 743
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017744684513892103,
      "loss": 2.1094,
      "step": 744
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017738024465519025,
      "loss": 2.0532,
      "step": 745
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017731355851695696,
      "loss": 2.0011,
      "step": 746
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017724678679803803,
      "loss": 2.0671,
      "step": 747
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017717992957234506,
      "loss": 2.0308,
      "step": 748
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017711298691388431,
      "loss": 1.9415,
      "step": 749
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017704595889675662,
      "loss": 2.0606,
      "step": 750
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.001769788455951573,
      "loss": 2.0442,
      "step": 751
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017691164708337603,
      "loss": 2.0792,
      "step": 752
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017684436343579691,
      "loss": 2.0979,
      "step": 753
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0017677699472689816,
      "loss": 2.0941,
      "step": 754
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017670954103125225,
      "loss": 2.1527,
      "step": 755
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017664200242352571,
      "loss": 2.0311,
      "step": 756
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017657437897847896,
      "loss": 2.0873,
      "step": 757
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017650667077096652,
      "loss": 1.9802,
      "step": 758
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017643887787593654,
      "loss": 2.0394,
      "step": 759
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00176371000368431,
      "loss": 2.0801,
      "step": 760
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017630303832358559,
      "loss": 1.9778,
      "step": 761
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001762349918166295,
      "loss": 2.0216,
      "step": 762
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017616686092288543,
      "loss": 2.0338,
      "step": 763
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017609864571776952,
      "loss": 2.0074,
      "step": 764
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001760303462767912,
      "loss": 2.0378,
      "step": 765
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017596196267555318,
      "loss": 1.9877,
      "step": 766
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017589349498975128,
      "loss": 2.0811,
      "step": 767
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017582494329517445,
      "loss": 2.0613,
      "step": 768
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017575630766770458,
      "loss": 2.0206,
      "step": 769
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017568758818331657,
      "loss": 2.0058,
      "step": 770
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017561878491807797,
      "loss": 2.1282,
      "step": 771
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001755498979481492,
      "loss": 1.9862,
      "step": 772
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017548092734978333,
      "loss": 2.0444,
      "step": 773
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017541187319932594,
      "loss": 2.1242,
      "step": 774
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017534273557321515,
      "loss": 2.0656,
      "step": 775
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017527351454798149,
      "loss": 2.0131,
      "step": 776
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017520421020024773,
      "loss": 1.985,
      "step": 777
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017513482260672895,
      "loss": 2.0947,
      "step": 778
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017506535184423232,
      "loss": 2.0473,
      "step": 779
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017499579798965713,
      "loss": 2.0392,
      "step": 780
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001749261611199946,
      "loss": 2.0844,
      "step": 781
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017485644131232786,
      "loss": 2.0488,
      "step": 782
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017478663864383185,
      "loss": 2.0629,
      "step": 783
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017471675319177323,
      "loss": 2.0638,
      "step": 784
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0017464678503351031,
      "loss": 2.0639,
      "step": 785
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001745767342464929,
      "loss": 2.067,
      "step": 786
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017450660090826233,
      "loss": 2.0737,
      "step": 787
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017443638509645127,
      "loss": 2.0523,
      "step": 788
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017436608688878373,
      "loss": 2.0402,
      "step": 789
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017429570636307483,
      "loss": 1.9324,
      "step": 790
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017422524359723096,
      "loss": 2.0161,
      "step": 791
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017415469866924938,
      "loss": 2.0163,
      "step": 792
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017408407165721842,
      "loss": 2.0858,
      "step": 793
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017401336263931722,
      "loss": 2.0924,
      "step": 794
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017394257169381568,
      "loss": 2.0344,
      "step": 795
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017387169889907445,
      "loss": 2.1021,
      "step": 796
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001738007443335447,
      "loss": 1.9772,
      "step": 797
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017372970807576823,
      "loss": 2.0394,
      "step": 798
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017365859020437712,
      "loss": 2.0795,
      "step": 799
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017358739079809387,
      "loss": 2.0934,
      "step": 800
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017351610993573123,
      "loss": 2.0364,
      "step": 801
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017344474769619219,
      "loss": 2.023,
      "step": 802
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017337330415846963,
      "loss": 2.1036,
      "step": 803
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017330177940164662,
      "loss": 2.0484,
      "step": 804
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00173230173504896,
      "loss": 2.0979,
      "step": 805
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017315848654748049,
      "loss": 2.0145,
      "step": 806
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001730867186087525,
      "loss": 2.0225,
      "step": 807
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017301486976815418,
      "loss": 2.0018,
      "step": 808
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017294294010521706,
      "loss": 1.9747,
      "step": 809
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017287092969956231,
      "loss": 2.0119,
      "step": 810
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017279883863090034,
      "loss": 2.0334,
      "step": 811
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017272666697903092,
      "loss": 1.9868,
      "step": 812
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00172654414823843,
      "loss": 2.1112,
      "step": 813
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017258208224531471,
      "loss": 2.0737,
      "step": 814
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0017250966932351305,
      "loss": 2.0365,
      "step": 815
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001724371761385941,
      "loss": 2.0486,
      "step": 816
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001723646027708027,
      "loss": 2.0915,
      "step": 817
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017229194930047252,
      "loss": 2.0019,
      "step": 818
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001722192158080258,
      "loss": 2.0255,
      "step": 819
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017214640237397348,
      "loss": 2.0989,
      "step": 820
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017207350907891483,
      "loss": 2.0892,
      "step": 821
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001720005360035377,
      "loss": 2.0169,
      "step": 822
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017192748322861814,
      "loss": 1.9828,
      "step": 823
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001718543508350204,
      "loss": 2.0409,
      "step": 824
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00171781138903697,
      "loss": 2.0528,
      "step": 825
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017170784751568836,
      "loss": 2.0066,
      "step": 826
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017163447675212287,
      "loss": 2.0489,
      "step": 827
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001715610266942169,
      "loss": 2.0423,
      "step": 828
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017148749742327443,
      "loss": 2.0851,
      "step": 829
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017141388902068724,
      "loss": 2.0734,
      "step": 830
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001713402015679347,
      "loss": 1.9922,
      "step": 831
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001712664351465836,
      "loss": 2.0418,
      "step": 832
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017119258983828822,
      "loss": 2.0579,
      "step": 833
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017111866572479012,
      "loss": 2.0888,
      "step": 834
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017104466288791814,
      "loss": 2.0849,
      "step": 835
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017097058140958818,
      "loss": 1.9614,
      "step": 836
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001708964213718033,
      "loss": 2.0426,
      "step": 837
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017082218285665342,
      "loss": 2.0164,
      "step": 838
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017074786594631535,
      "loss": 2.0245,
      "step": 839
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017067347072305275,
      "loss": 1.9837,
      "step": 840
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017059899726921586,
      "loss": 1.9614,
      "step": 841
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.001705244456672416,
      "loss": 1.9895,
      "step": 842
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017044981599965336,
      "loss": 2.0404,
      "step": 843
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017037510834906095,
      "loss": 1.9788,
      "step": 844
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017030032279816048,
      "loss": 1.9829,
      "step": 845
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0017022545942973434,
      "loss": 2.0822,
      "step": 846
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00170150518326651,
      "loss": 2.0808,
      "step": 847
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0017007549957186497,
      "loss": 1.9744,
      "step": 848
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001700004032484168,
      "loss": 1.9659,
      "step": 849
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016992522943943288,
      "loss": 2.0823,
      "step": 850
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001698499782281253,
      "loss": 2.0644,
      "step": 851
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016977464969779189,
      "loss": 1.9693,
      "step": 852
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00169699243931816,
      "loss": 1.9847,
      "step": 853
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016962376101366658,
      "loss": 2.0562,
      "step": 854
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001695482010268979,
      "loss": 2.05,
      "step": 855
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016947256405514955,
      "loss": 1.9587,
      "step": 856
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016939685018214638,
      "loss": 2.0701,
      "step": 857
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016932105949169836,
      "loss": 2.0174,
      "step": 858
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001692451920677004,
      "loss": 2.0718,
      "step": 859
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016916924799413246,
      "loss": 2.0063,
      "step": 860
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001690932273550593,
      "loss": 2.1098,
      "step": 861
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016901713023463039,
      "loss": 2.0831,
      "step": 862
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016894095671707997,
      "loss": 2.033,
      "step": 863
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016886470688672675,
      "loss": 2.0062,
      "step": 864
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016878838082797394,
      "loss": 2.0567,
      "step": 865
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016871197862530917,
      "loss": 2.1234,
      "step": 866
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016863550036330423,
      "loss": 1.9374,
      "step": 867
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016855894612661526,
      "loss": 1.9981,
      "step": 868
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016848231599998244,
      "loss": 1.9936,
      "step": 869
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001684056100682299,
      "loss": 2.0159,
      "step": 870
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016832882841626576,
      "loss": 2.0351,
      "step": 871
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001682519711290819,
      "loss": 2.011,
      "step": 872
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016817503829175396,
      "loss": 2.0628,
      "step": 873
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001680980299894412,
      "loss": 2.0178,
      "step": 874
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016802094630738638,
      "loss": 2.0679,
      "step": 875
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016794378733091574,
      "loss": 2.0575,
      "step": 876
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0016786655314543885,
      "loss": 2.0209,
      "step": 877
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016778924383644856,
      "loss": 2.0074,
      "step": 878
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016771185948952084,
      "loss": 1.9977,
      "step": 879
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016763440019031473,
      "loss": 2.0499,
      "step": 880
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016755686602457224,
      "loss": 2.1481,
      "step": 881
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016747925707811821,
      "loss": 2.0516,
      "step": 882
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001674015734368604,
      "loss": 2.0164,
      "step": 883
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016732381518678905,
      "loss": 2.0543,
      "step": 884
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016724598241397715,
      "loss": 2.1101,
      "step": 885
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001671680752045801,
      "loss": 1.9813,
      "step": 886
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016709009364483571,
      "loss": 1.9541,
      "step": 887
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016701203782106414,
      "loss": 1.9764,
      "step": 888
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016693390781966763,
      "loss": 1.9972,
      "step": 889
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016685570372713067,
      "loss": 2.0543,
      "step": 890
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016677742563001967,
      "loss": 2.0023,
      "step": 891
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016669907361498303,
      "loss": 2.0858,
      "step": 892
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001666206477687509,
      "loss": 2.0117,
      "step": 893
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001665421481781352,
      "loss": 1.998,
      "step": 894
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016646357493002948,
      "loss": 2.0418,
      "step": 895
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016638492811140882,
      "loss": 2.0105,
      "step": 896
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016630620780932973,
      "loss": 2.0061,
      "step": 897
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016622741411093003,
      "loss": 1.9732,
      "step": 898
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016614854710342883,
      "loss": 2.1028,
      "step": 899
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001660696068741264,
      "loss": 1.9858,
      "step": 900
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016599059351040401,
      "loss": 2.0482,
      "step": 901
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016591150709972392,
      "loss": 2.0773,
      "step": 902
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016583234772962925,
      "loss": 2.0712,
      "step": 903
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016575311548774386,
      "loss": 2.0349,
      "step": 904
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016567381046177225,
      "loss": 1.9795,
      "step": 905
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016559443273949956,
      "loss": 1.9657,
      "step": 906
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0016551498240879137,
      "loss": 2.0245,
      "step": 907
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001654354595575936,
      "loss": 2.0728,
      "step": 908
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016535586427393247,
      "loss": 2.1016,
      "step": 909
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016527619664591438,
      "loss": 2.0334,
      "step": 910
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016519645676172578,
      "loss": 2.0691,
      "step": 911
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016511664470963317,
      "loss": 2.0981,
      "step": 912
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016503676057798287,
      "loss": 2.0655,
      "step": 913
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016495680445520102,
      "loss": 1.9478,
      "step": 914
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016487677642979342,
      "loss": 2.0232,
      "step": 915
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001647966765903455,
      "loss": 2.0313,
      "step": 916
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016471650502552216,
      "loss": 2.0185,
      "step": 917
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001646362618240677,
      "loss": 2.059,
      "step": 918
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001645559470748057,
      "loss": 1.9495,
      "step": 919
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016447556086663896,
      "loss": 2.0281,
      "step": 920
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016439510328854939,
      "loss": 2.0314,
      "step": 921
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016431457442959783,
      "loss": 2.0735,
      "step": 922
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016423397437892416,
      "loss": 2.016,
      "step": 923
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016415330322574688,
      "loss": 1.9945,
      "step": 924
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001640725610593634,
      "loss": 1.9628,
      "step": 925
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001639917479691496,
      "loss": 2.1126,
      "step": 926
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016391086404455987,
      "loss": 2.0264,
      "step": 927
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016382990937512708,
      "loss": 2.063,
      "step": 928
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016374888405046232,
      "loss": 1.9318,
      "step": 929
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016366778816025503,
      "loss": 2.0521,
      "step": 930
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016358662179427256,
      "loss": 2.0269,
      "step": 931
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016350538504236046,
      "loss": 1.9622,
      "step": 932
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001634240779944421,
      "loss": 1.952,
      "step": 933
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016334270074051867,
      "loss": 1.9759,
      "step": 934
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.001632612533706691,
      "loss": 2.0239,
      "step": 935
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016317973597504984,
      "loss": 2.0278,
      "step": 936
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016309814864389502,
      "loss": 2.0246,
      "step": 937
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016301649146751606,
      "loss": 2.0563,
      "step": 938
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0016293476453630173,
      "loss": 2.0648,
      "step": 939
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016285296794071797,
      "loss": 2.0096,
      "step": 940
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016277110177130797,
      "loss": 2.0187,
      "step": 941
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016268916611869174,
      "loss": 2.0163,
      "step": 942
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001626071610735663,
      "loss": 2.0691,
      "step": 943
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016252508672670557,
      "loss": 2.0106,
      "step": 944
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016244294316896002,
      "loss": 2.0341,
      "step": 945
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001623607304912568,
      "loss": 2.0082,
      "step": 946
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016227844878459964,
      "loss": 2.0171,
      "step": 947
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016219609814006857,
      "loss": 2.0542,
      "step": 948
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016211367864881999,
      "loss": 1.9994,
      "step": 949
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016203119040208646,
      "loss": 1.9499,
      "step": 950
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016194863349117674,
      "loss": 2.0921,
      "step": 951
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001618660080074755,
      "loss": 2.0784,
      "step": 952
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001617833140424434,
      "loss": 1.9804,
      "step": 953
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016170055168761677,
      "loss": 1.9987,
      "step": 954
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016161772103460783,
      "loss": 2.0856,
      "step": 955
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016153482217510424,
      "loss": 1.9937,
      "step": 956
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016145185520086926,
      "loss": 2.0427,
      "step": 957
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016136882020374146,
      "loss": 2.0539,
      "step": 958
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001612857172756348,
      "loss": 1.995,
      "step": 959
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016120254650853838,
      "loss": 1.9856,
      "step": 960
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001611193079945164,
      "loss": 2.0195,
      "step": 961
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016103600182570809,
      "loss": 2.006,
      "step": 962
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016095262809432747,
      "loss": 2.0073,
      "step": 963
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016086918689266346,
      "loss": 1.9973,
      "step": 964
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016078567831307958,
      "loss": 2.0317,
      "step": 965
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016070210244801403,
      "loss": 2.0073,
      "step": 966
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016061845938997934,
      "loss": 2.0555,
      "step": 967
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016053474923156262,
      "loss": 2.0758,
      "step": 968
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0016045097206542503,
      "loss": 2.0127,
      "step": 969
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0016036712798430206,
      "loss": 2.0527,
      "step": 970
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0016028321708100328,
      "loss": 2.0459,
      "step": 971
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0016019923944841214,
      "loss": 1.9874,
      "step": 972
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0016011519517948592,
      "loss": 2.0796,
      "step": 973
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0016003108436725582,
      "loss": 1.9989,
      "step": 974
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015994690710482656,
      "loss": 2.072,
      "step": 975
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001598626634853765,
      "loss": 1.9538,
      "step": 976
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001597783536021574,
      "loss": 1.9828,
      "step": 977
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015969397754849435,
      "loss": 2.059,
      "step": 978
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015960953541778577,
      "loss": 2.0429,
      "step": 979
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015952502730350315,
      "loss": 2.1043,
      "step": 980
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015944045329919108,
      "loss": 2.0179,
      "step": 981
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00159355813498467,
      "loss": 2.045,
      "step": 982
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015927110799502126,
      "loss": 2.0576,
      "step": 983
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015918633688261693,
      "loss": 2.0109,
      "step": 984
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001591015002550896,
      "loss": 2.0253,
      "step": 985
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015901659820634758,
      "loss": 2.0242,
      "step": 986
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015893163083037138,
      "loss": 2.0606,
      "step": 987
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015884659822121402,
      "loss": 2.0031,
      "step": 988
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015876150047300058,
      "loss": 1.9624,
      "step": 989
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001586763376799283,
      "loss": 1.8883,
      "step": 990
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015859110993626639,
      "loss": 2.0278,
      "step": 991
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015850581733635604,
      "loss": 2.0463,
      "step": 992
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015842045997461014,
      "loss": 2.0236,
      "step": 993
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001583350379455133,
      "loss": 2.0282,
      "step": 994
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015824955134362173,
      "loss": 2.049,
      "step": 995
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015816400026356313,
      "loss": 2.0532,
      "step": 996
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015807838480003647,
      "loss": 1.9822,
      "step": 997
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001579927050478121,
      "loss": 1.9679,
      "step": 998
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015790696110173153,
      "loss": 1.9687,
      "step": 999
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0015782115305670722,
      "loss": 1.9639,
      "step": 1000
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001577352810077227,
      "loss": 2.0357,
      "step": 1001
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015764934504983233,
      "loss": 1.98,
      "step": 1002
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015756334527816111,
      "loss": 2.0457,
      "step": 1003
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015747728178790487,
      "loss": 1.9957,
      "step": 1004
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015739115467432977,
      "loss": 2.0154,
      "step": 1005
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015730496403277246,
      "loss": 2.0913,
      "step": 1006
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015721870995864,
      "loss": 2.0419,
      "step": 1007
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015713239254740957,
      "loss": 1.9615,
      "step": 1008
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015704601189462848,
      "loss": 1.9704,
      "step": 1009
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015695956809591407,
      "loss": 2.053,
      "step": 1010
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015687306124695358,
      "loss": 2.0259,
      "step": 1011
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015678649144350398,
      "loss": 2.0405,
      "step": 1012
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00156699858781392,
      "loss": 2.0716,
      "step": 1013
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001566131633565139,
      "loss": 2.0552,
      "step": 1014
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015652640526483542,
      "loss": 2.0201,
      "step": 1015
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015643958460239175,
      "loss": 2.0713,
      "step": 1016
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001563527014652872,
      "loss": 2.0092,
      "step": 1017
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015626575594969534,
      "loss": 2.0398,
      "step": 1018
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015617874815185876,
      "loss": 1.9917,
      "step": 1019
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015609167816808896,
      "loss": 1.9813,
      "step": 1020
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015600454609476632,
      "loss": 1.9978,
      "step": 1021
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015591735202833993,
      "loss": 2.0162,
      "step": 1022
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015583009606532753,
      "loss": 1.9905,
      "step": 1023
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015574277830231536,
      "loss": 2.0013,
      "step": 1024
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015565539883595795,
      "loss": 1.9829,
      "step": 1025
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001555679577629784,
      "loss": 1.984,
      "step": 1026
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015548045518016772,
      "loss": 2.0158,
      "step": 1027
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.001553928911843852,
      "loss": 2.0539,
      "step": 1028
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00155305265872558,
      "loss": 2.0014,
      "step": 1029
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015521757934168117,
      "loss": 2.0275,
      "step": 1030
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0015512983168881763,
      "loss": 2.0362,
      "step": 1031
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001550420230110978,
      "loss": 2.0073,
      "step": 1032
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015495415340571978,
      "loss": 1.985,
      "step": 1033
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015486622296994902,
      "loss": 2.0294,
      "step": 1034
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001547782318011184,
      "loss": 2.0242,
      "step": 1035
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015469017999662786,
      "loss": 2.1605,
      "step": 1036
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001546020676539447,
      "loss": 2.0412,
      "step": 1037
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015451389487060303,
      "loss": 2.0022,
      "step": 1038
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015442566174420397,
      "loss": 1.8891,
      "step": 1039
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015433736837241535,
      "loss": 1.9468,
      "step": 1040
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001542490148529718,
      "loss": 2.0402,
      "step": 1041
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015416060128367439,
      "loss": 2.0142,
      "step": 1042
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015407212776239083,
      "loss": 1.9723,
      "step": 1043
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015398359438705503,
      "loss": 2.0277,
      "step": 1044
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015389500125566726,
      "loss": 1.9853,
      "step": 1045
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001538063484662939,
      "loss": 2.0016,
      "step": 1046
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015371763611706738,
      "loss": 2.0508,
      "step": 1047
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00153628864306186,
      "loss": 1.9874,
      "step": 1048
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00153540033131914,
      "loss": 1.9831,
      "step": 1049
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015345114269258119,
      "loss": 2.0246,
      "step": 1050
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015336219308658308,
      "loss": 2.0445,
      "step": 1051
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015327318441238065,
      "loss": 2.0632,
      "step": 1052
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015318411676850025,
      "loss": 1.9734,
      "step": 1053
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001530949902535335,
      "loss": 2.0183,
      "step": 1054
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015300580496613726,
      "loss": 2.0284,
      "step": 1055
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015291656100503328,
      "loss": 1.9821,
      "step": 1056
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015282725846900848,
      "loss": 2.0234,
      "step": 1057
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015273789745691442,
      "loss": 2.0154,
      "step": 1058
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015264847806766748,
      "loss": 2.0215,
      "step": 1059
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015255900040024868,
      "loss": 2.04,
      "step": 1060
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015246946455370351,
      "loss": 2.0196,
      "step": 1061
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0015237987062714188,
      "loss": 1.9766,
      "step": 1062
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015229021871973796,
      "loss": 1.9926,
      "step": 1063
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015220050893073017,
      "loss": 2.0742,
      "step": 1064
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015211074135942089,
      "loss": 2.009,
      "step": 1065
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015202091610517655,
      "loss": 2.0281,
      "step": 1066
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015193103326742743,
      "loss": 2.0399,
      "step": 1067
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015184109294566748,
      "loss": 1.9765,
      "step": 1068
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015175109523945436,
      "loss": 2.0569,
      "step": 1069
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015166104024840921,
      "loss": 2.0083,
      "step": 1070
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001515709280722166,
      "loss": 2.0653,
      "step": 1071
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015148075881062436,
      "loss": 2.0948,
      "step": 1072
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015139053256344353,
      "loss": 2.0503,
      "step": 1073
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015130024943054829,
      "loss": 2.0199,
      "step": 1074
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015120990951187569,
      "loss": 2.0135,
      "step": 1075
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001511195129074257,
      "loss": 1.99,
      "step": 1076
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00151029059717261,
      "loss": 2.0824,
      "step": 1077
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015093855004150694,
      "loss": 1.9533,
      "step": 1078
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015084798398035137,
      "loss": 2.0089,
      "step": 1079
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001507573616340446,
      "loss": 1.9756,
      "step": 1080
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001506666831028992,
      "loss": 2.0406,
      "step": 1081
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001505759484872899,
      "loss": 1.9923,
      "step": 1082
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015048515788765363,
      "loss": 2.0256,
      "step": 1083
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015039431140448914,
      "loss": 1.9454,
      "step": 1084
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015030340913835714,
      "loss": 1.8891,
      "step": 1085
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015021245118988006,
      "loss": 2.0098,
      "step": 1086
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00150121437659742,
      "loss": 1.9624,
      "step": 1087
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0015003036864868848,
      "loss": 2.0595,
      "step": 1088
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001499392442575266,
      "loss": 2.0075,
      "step": 1089
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0014984806458712462,
      "loss": 2.0028,
      "step": 1090
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0014975682973841198,
      "loss": 2.0614,
      "step": 1091
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0014966553981237939,
      "loss": 1.9329,
      "step": 1092
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0014957419491007826,
      "loss": 1.9608,
      "step": 1093
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014948279513262112,
      "loss": 2.0344,
      "step": 1094
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00149391340581181,
      "loss": 2.0103,
      "step": 1095
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014929983135699171,
      "loss": 1.9721,
      "step": 1096
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014920826756134758,
      "loss": 2.0514,
      "step": 1097
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014911664929560323,
      "loss": 1.9663,
      "step": 1098
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014902497666117373,
      "loss": 2.021,
      "step": 1099
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014893324975953424,
      "loss": 1.9644,
      "step": 1100
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014884146869221994,
      "loss": 2.0091,
      "step": 1101
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014874963356082613,
      "loss": 1.9863,
      "step": 1102
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014865774446700779,
      "loss": 2.0192,
      "step": 1103
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014856580151247974,
      "loss": 2.0566,
      "step": 1104
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014847380479901635,
      "loss": 2.0313,
      "step": 1105
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014838175442845151,
      "loss": 1.9868,
      "step": 1106
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014828965050267858,
      "loss": 1.9982,
      "step": 1107
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014819749312365012,
      "loss": 2.0108,
      "step": 1108
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001481052823933779,
      "loss": 2.051,
      "step": 1109
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014801301841393267,
      "loss": 2.0192,
      "step": 1110
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014792070128744426,
      "loss": 2.0647,
      "step": 1111
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014782833111610118,
      "loss": 2.0251,
      "step": 1112
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014773590800215078,
      "loss": 2.0373,
      "step": 1113
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014764343204789897,
      "loss": 2.0194,
      "step": 1114
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014755090335571012,
      "loss": 1.9797,
      "step": 1115
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014745832202800698,
      "loss": 2.0239,
      "step": 1116
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001473656881672706,
      "loss": 1.965,
      "step": 1117
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014727300187604023,
      "loss": 2.0354,
      "step": 1118
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00147180263256913,
      "loss": 1.982,
      "step": 1119
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001470874724125441,
      "loss": 2.0237,
      "step": 1120
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.001469946294456465,
      "loss": 2.0158,
      "step": 1121
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014690173445899078,
      "loss": 2.0874,
      "step": 1122
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0014680878755540525,
      "loss": 2.0106,
      "step": 1123
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001467157888377756,
      "loss": 1.9722,
      "step": 1124
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014662273840904488,
      "loss": 1.9701,
      "step": 1125
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014652963637221336,
      "loss": 1.9799,
      "step": 1126
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001464364828303385,
      "loss": 1.9885,
      "step": 1127
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001463432778865347,
      "loss": 1.9631,
      "step": 1128
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014625002164397331,
      "loss": 2.0582,
      "step": 1129
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014615671420588248,
      "loss": 2.038,
      "step": 1130
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014606335567554697,
      "loss": 1.9949,
      "step": 1131
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001459699461563081,
      "loss": 2.0568,
      "step": 1132
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014587648575156368,
      "loss": 2.0067,
      "step": 1133
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014578297456476783,
      "loss": 1.9899,
      "step": 1134
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014568941269943085,
      "loss": 2.0568,
      "step": 1135
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001455958002591192,
      "loss": 2.0517,
      "step": 1136
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014550213734745524,
      "loss": 1.9748,
      "step": 1137
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014540842406811727,
      "loss": 2.0441,
      "step": 1138
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014531466052483933,
      "loss": 2.028,
      "step": 1139
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014522084682141102,
      "loss": 1.9636,
      "step": 1140
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001451269830616776,
      "loss": 2.057,
      "step": 1141
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014503306934953964,
      "loss": 1.9922,
      "step": 1142
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014493910578895304,
      "loss": 1.9878,
      "step": 1143
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014484509248392885,
      "loss": 2.0342,
      "step": 1144
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001447510295385332,
      "loss": 2.0465,
      "step": 1145
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014465691705688722,
      "loss": 2.0625,
      "step": 1146
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014456275514316676,
      "loss": 1.9494,
      "step": 1147
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014446854390160252,
      "loss": 1.9777,
      "step": 1148
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014437428343647967,
      "loss": 2.0052,
      "step": 1149
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014427997385213797,
      "loss": 2.0681,
      "step": 1150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014418561525297152,
      "loss": 1.963,
      "step": 1151
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014409120774342863,
      "loss": 2.0661,
      "step": 1152
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0014399675142801184,
      "loss": 2.0275,
      "step": 1153
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001439022464112776,
      "loss": 2.0133,
      "step": 1154
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014380769279783642,
      "loss": 1.8741,
      "step": 1155
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014371309069235246,
      "loss": 2.0688,
      "step": 1156
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014361844019954361,
      "loss": 1.9904,
      "step": 1157
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014352374142418138,
      "loss": 2.0021,
      "step": 1158
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014342899447109061,
      "loss": 1.9533,
      "step": 1159
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014333419944514956,
      "loss": 1.9781,
      "step": 1160
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014323935645128964,
      "loss": 1.9872,
      "step": 1161
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014314446559449549,
      "loss": 1.9809,
      "step": 1162
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001430495269798045,
      "loss": 1.9728,
      "step": 1163
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001429545407123071,
      "loss": 1.9641,
      "step": 1164
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001428595068971465,
      "loss": 1.9972,
      "step": 1165
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014276442563951838,
      "loss": 1.9798,
      "step": 1166
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014266929704467104,
      "loss": 1.9755,
      "step": 1167
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014257412121790518,
      "loss": 1.9785,
      "step": 1168
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014247889826457373,
      "loss": 1.8916,
      "step": 1169
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014238362829008188,
      "loss": 1.9922,
      "step": 1170
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014228831139988679,
      "loss": 2.0204,
      "step": 1171
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014219294769949751,
      "loss": 1.9211,
      "step": 1172
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00142097537294475,
      "loss": 2.015,
      "step": 1173
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014200208029043196,
      "loss": 2.0603,
      "step": 1174
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001419065767930325,
      "loss": 1.9147,
      "step": 1175
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001418110269079923,
      "loss": 1.9916,
      "step": 1176
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014171543074107844,
      "loss": 1.99,
      "step": 1177
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014161978839810911,
      "loss": 2.0503,
      "step": 1178
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001415240999849537,
      "loss": 1.9902,
      "step": 1179
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001414283656075326,
      "loss": 2.0639,
      "step": 1180
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00141332585371817,
      "loss": 1.9997,
      "step": 1181
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001412367593838289,
      "loss": 2.0602,
      "step": 1182
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014114088774964098,
      "loss": 2.013,
      "step": 1183
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001410449705753764,
      "loss": 2.0103,
      "step": 1184
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0014094900796720875,
      "loss": 2.0447,
      "step": 1185
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0014085300003136192,
      "loss": 1.9033,
      "step": 1186
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0014075694687410991,
      "loss": 2.088,
      "step": 1187
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0014066084860177685,
      "loss": 2.0176,
      "step": 1188
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001405647053207368,
      "loss": 2.0587,
      "step": 1189
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0014046851713741366,
      "loss": 2.0514,
      "step": 1190
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0014037228415828093,
      "loss": 2.0531,
      "step": 1191
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0014027600648986178,
      "loss": 2.0269,
      "step": 1192
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0014017968423872891,
      "loss": 2.0331,
      "step": 1193
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001400833175115042,
      "loss": 2.025,
      "step": 1194
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001399869064148589,
      "loss": 2.0136,
      "step": 1195
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013989045105551332,
      "loss": 2.0268,
      "step": 1196
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013979395154023679,
      "loss": 2.0279,
      "step": 1197
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013969740797584746,
      "loss": 2.0766,
      "step": 1198
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013960082046921237,
      "loss": 1.9513,
      "step": 1199
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013950418912724704,
      "loss": 1.9501,
      "step": 1200
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001394075140569156,
      "loss": 1.9918,
      "step": 1201
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013931079536523062,
      "loss": 1.9786,
      "step": 1202
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013921403315925282,
      "loss": 2.0267,
      "step": 1203
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013911722754609125,
      "loss": 1.9994,
      "step": 1204
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001390203786329029,
      "loss": 2.0059,
      "step": 1205
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013892348652689275,
      "loss": 2.0365,
      "step": 1206
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001388265513353135,
      "loss": 2.0477,
      "step": 1207
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013872957316546568,
      "loss": 2.0306,
      "step": 1208
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001386325521246973,
      "loss": 2.0996,
      "step": 1209
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.001385354883204038,
      "loss": 1.9904,
      "step": 1210
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013843838186002803,
      "loss": 2.0014,
      "step": 1211
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013834123285106008,
      "loss": 2.0599,
      "step": 1212
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00138244041401037,
      "loss": 2.047,
      "step": 1213
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013814680761754297,
      "loss": 2.0283,
      "step": 1214
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013804953160820896,
      "loss": 1.9967,
      "step": 1215
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0013795221348071268,
      "loss": 1.9557,
      "step": 1216
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013785485334277844,
      "loss": 2.0205,
      "step": 1217
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013775745130217717,
      "loss": 2.0258,
      "step": 1218
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013766000746672597,
      "loss": 2.0265,
      "step": 1219
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013756252194428841,
      "loss": 2.0056,
      "step": 1220
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013746499484277416,
      "loss": 1.9276,
      "step": 1221
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001373674262701388,
      "loss": 1.957,
      "step": 1222
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013726981633438392,
      "loss": 2.0044,
      "step": 1223
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013717216514355691,
      "loss": 2.0336,
      "step": 1224
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001370744728057507,
      "loss": 1.9889,
      "step": 1225
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013697673942910393,
      "loss": 2.0155,
      "step": 1226
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013687896512180058,
      "loss": 2.0261,
      "step": 1227
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013678114999206995,
      "loss": 2.0001,
      "step": 1228
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001366832941481865,
      "loss": 1.9393,
      "step": 1229
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013658539769846982,
      "loss": 2.0375,
      "step": 1230
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001364874607512844,
      "loss": 2.0222,
      "step": 1231
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013638948341503953,
      "loss": 2.0127,
      "step": 1232
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013629146579818932,
      "loss": 1.9215,
      "step": 1233
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013619340800923236,
      "loss": 1.9821,
      "step": 1234
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013609531015671172,
      "loss": 1.9702,
      "step": 1235
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013599717234921488,
      "loss": 2.0184,
      "step": 1236
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013589899469537347,
      "loss": 1.9623,
      "step": 1237
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013580077730386334,
      "loss": 1.953,
      "step": 1238
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013570252028340412,
      "loss": 1.9951,
      "step": 1239
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001356042237427596,
      "loss": 2.0159,
      "step": 1240
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013550588779073702,
      "loss": 2.0313,
      "step": 1241
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013540751253618747,
      "loss": 1.9782,
      "step": 1242
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001353090980880054,
      "loss": 1.9998,
      "step": 1243
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013521064455512871,
      "loss": 1.9969,
      "step": 1244
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013511215204653855,
      "loss": 2.0083,
      "step": 1245
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0013501362067125928,
      "loss": 2.0131,
      "step": 1246
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013491505053835813,
      "loss": 2.0603,
      "step": 1247
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013481644175694538,
      "loss": 2.0423,
      "step": 1248
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013471779443617405,
      "loss": 1.9505,
      "step": 1249
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013461910868523973,
      "loss": 1.9587,
      "step": 1250
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013452038461338068,
      "loss": 1.9823,
      "step": 1251
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001344216223298775,
      "loss": 1.9609,
      "step": 1252
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013432282194405314,
      "loss": 2.0465,
      "step": 1253
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013422398356527263,
      "loss": 2.0799,
      "step": 1254
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001341251073029432,
      "loss": 2.0065,
      "step": 1255
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001340261932665139,
      "loss": 2.0182,
      "step": 1256
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013392724156547561,
      "loss": 1.9894,
      "step": 1257
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013382825230936098,
      "loss": 1.9858,
      "step": 1258
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013372922560774408,
      "loss": 1.9982,
      "step": 1259
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013363016157024062,
      "loss": 1.9088,
      "step": 1260
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013353106030650746,
      "loss": 2.0551,
      "step": 1261
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013343192192624281,
      "loss": 1.9906,
      "step": 1262
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013333274653918586,
      "loss": 2.0496,
      "step": 1263
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013323353425511685,
      "loss": 2.0294,
      "step": 1264
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013313428518385677,
      "loss": 1.9883,
      "step": 1265
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001330349994352674,
      "loss": 1.9851,
      "step": 1266
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013293567711925107,
      "loss": 1.9623,
      "step": 1267
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001328363183457507,
      "loss": 2.0594,
      "step": 1268
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001327369232247494,
      "loss": 1.967,
      "step": 1269
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013263749186627062,
      "loss": 1.9893,
      "step": 1270
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001325380243803779,
      "loss": 2.0666,
      "step": 1271
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013243852087717477,
      "loss": 1.9702,
      "step": 1272
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013233898146680462,
      "loss": 2.052,
      "step": 1273
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013223940625945061,
      "loss": 2.0043,
      "step": 1274
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001321397953653355,
      "loss": 2.0051,
      "step": 1275
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013204014889472155,
      "loss": 2.0256,
      "step": 1276
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0013194046695791046,
      "loss": 1.9546,
      "step": 1277
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013184074966524312,
      "loss": 2.002,
      "step": 1278
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013174099712709953,
      "loss": 1.9202,
      "step": 1279
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013164120945389876,
      "loss": 2.0351,
      "step": 1280
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013154138675609886,
      "loss": 2.004,
      "step": 1281
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013144152914419645,
      "loss": 1.9978,
      "step": 1282
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013134163672872692,
      "loss": 2.063,
      "step": 1283
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013124170962026422,
      "loss": 2.0069,
      "step": 1284
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001311417479294206,
      "loss": 1.9839,
      "step": 1285
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013104175176684666,
      "loss": 2.0162,
      "step": 1286
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013094172124323111,
      "loss": 1.9585,
      "step": 1287
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013084165646930074,
      "loss": 2.103,
      "step": 1288
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013074155755582021,
      "loss": 1.9457,
      "step": 1289
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013064142461359208,
      "loss": 1.9966,
      "step": 1290
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013054125775345637,
      "loss": 1.959,
      "step": 1291
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013044105708629088,
      "loss": 1.9806,
      "step": 1292
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013034082272301067,
      "loss": 1.9473,
      "step": 1293
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013024055477456812,
      "loss": 2.0249,
      "step": 1294
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013014025335195286,
      "loss": 1.9659,
      "step": 1295
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0013003991856619154,
      "loss": 1.9157,
      "step": 1296
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0012993955052834766,
      "loss": 2.0018,
      "step": 1297
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0012983914934952163,
      "loss": 2.0223,
      "step": 1298
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0012973871514085056,
      "loss": 1.9569,
      "step": 1299
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0012963824801350804,
      "loss": 2.0319,
      "step": 1300
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001295377480787041,
      "loss": 2.0382,
      "step": 1301
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0012943721544768512,
      "loss": 1.9724,
      "step": 1302
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0012933665023173373,
      "loss": 1.942,
      "step": 1303
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0012923605254216853,
      "loss": 2.0411,
      "step": 1304
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001291354224903441,
      "loss": 1.991,
      "step": 1305
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0012903476018765083,
      "loss": 1.9746,
      "step": 1306
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0012893406574551488,
      "loss": 1.968,
      "step": 1307
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0012883333927539793,
      "loss": 2.0716,
      "step": 1308
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012873258088879707,
      "loss": 1.9628,
      "step": 1309
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001286317906972448,
      "loss": 2.0546,
      "step": 1310
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012853096881230877,
      "loss": 1.9878,
      "step": 1311
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012843011534559175,
      "loss": 2.0741,
      "step": 1312
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012832923040873143,
      "loss": 1.9711,
      "step": 1313
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012822831411340042,
      "loss": 1.9684,
      "step": 1314
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001281273665713059,
      "loss": 2.0649,
      "step": 1315
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012802638789418976,
      "loss": 1.9661,
      "step": 1316
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012792537819382827,
      "loss": 2.0227,
      "step": 1317
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012782433758203216,
      "loss": 1.9672,
      "step": 1318
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012772326617064627,
      "loss": 2.0463,
      "step": 1319
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001276221640715495,
      "loss": 1.9925,
      "step": 1320
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012752103139665484,
      "loss": 1.9457,
      "step": 1321
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012741986825790907,
      "loss": 2.0159,
      "step": 1322
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012731867476729265,
      "loss": 1.961,
      "step": 1323
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012721745103681976,
      "loss": 1.9534,
      "step": 1324
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012711619717853785,
      "loss": 1.9441,
      "step": 1325
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012701491330452792,
      "loss": 1.9739,
      "step": 1326
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012691359952690408,
      "loss": 2.0727,
      "step": 1327
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001268122559578136,
      "loss": 2.0166,
      "step": 1328
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012671088270943666,
      "loss": 2.0199,
      "step": 1329
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012660947989398636,
      "loss": 2.0352,
      "step": 1330
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012650804762370854,
      "loss": 2.0114,
      "step": 1331
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012640658601088153,
      "loss": 1.9894,
      "step": 1332
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012630509516781626,
      "loss": 1.9212,
      "step": 1333
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012620357520685599,
      "loss": 2.0245,
      "step": 1334
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012610202624037618,
      "loss": 2.0623,
      "step": 1335
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012600044838078437,
      "loss": 1.9993,
      "step": 1336
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001258988417405202,
      "loss": 1.8532,
      "step": 1337
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012579720643205506,
      "loss": 1.9156,
      "step": 1338
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0012569554256789206,
      "loss": 1.9607,
      "step": 1339
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012559385026056607,
      "loss": 2.0242,
      "step": 1340
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012549212962264325,
      "loss": 2.0328,
      "step": 1341
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012539038076672122,
      "loss": 2.0363,
      "step": 1342
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012528860380542888,
      "loss": 1.9909,
      "step": 1343
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012518679885142614,
      "loss": 2.0149,
      "step": 1344
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012508496601740396,
      "loss": 2.0567,
      "step": 1345
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001249831054160841,
      "loss": 2.0063,
      "step": 1346
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012488121716021918,
      "loss": 2.1157,
      "step": 1347
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001247793013625923,
      "loss": 2.0076,
      "step": 1348
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001246773581360171,
      "loss": 1.9399,
      "step": 1349
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001245753875933376,
      "loss": 1.9105,
      "step": 1350
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00124473389847428,
      "loss": 1.8673,
      "step": 1351
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012437136501119268,
      "loss": 1.9691,
      "step": 1352
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00124269313197566,
      "loss": 2.0618,
      "step": 1353
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001241672345195121,
      "loss": 2.0361,
      "step": 1354
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012406512909002496,
      "loss": 2.0295,
      "step": 1355
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012396299702212815,
      "loss": 1.9439,
      "step": 1356
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012386083842887462,
      "loss": 1.9732,
      "step": 1357
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012375865342334682,
      "loss": 1.9754,
      "step": 1358
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012365644211865638,
      "loss": 1.9725,
      "step": 1359
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012355420462794406,
      "loss": 2.023,
      "step": 1360
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012345194106437956,
      "loss": 1.9284,
      "step": 1361
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012334965154116148,
      "loss": 1.9968,
      "step": 1362
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012324733617151713,
      "loss": 1.9491,
      "step": 1363
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001231449950687025,
      "loss": 2.0288,
      "step": 1364
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012304262834600195,
      "loss": 2.0097,
      "step": 1365
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012294023611672828,
      "loss": 2.0175,
      "step": 1366
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012283781849422254,
      "loss": 1.9664,
      "step": 1367
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001227353755918538,
      "loss": 1.978,
      "step": 1368
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001226329075230192,
      "loss": 1.9899,
      "step": 1369
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0012253041440114373,
      "loss": 2.0075,
      "step": 1370
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012242789633968001,
      "loss": 1.9994,
      "step": 1371
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001223253534521084,
      "loss": 2.0328,
      "step": 1372
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012222278585193667,
      "loss": 2.0019,
      "step": 1373
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012212019365269995,
      "loss": 2.0032,
      "step": 1374
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012201757696796063,
      "loss": 1.9528,
      "step": 1375
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012191493591130816,
      "loss": 1.9897,
      "step": 1376
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012181227059635898,
      "loss": 2.0043,
      "step": 1377
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012170958113675641,
      "loss": 1.9801,
      "step": 1378
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012160686764617048,
      "loss": 1.9816,
      "step": 1379
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001215041302382978,
      "loss": 2.0285,
      "step": 1380
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012140136902686147,
      "loss": 2.0051,
      "step": 1381
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012129858412561099,
      "loss": 1.9222,
      "step": 1382
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012119577564832199,
      "loss": 1.9954,
      "step": 1383
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012109294370879627,
      "loss": 2.0013,
      "step": 1384
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012099008842086155,
      "loss": 2.0537,
      "step": 1385
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012088720989837142,
      "loss": 1.9854,
      "step": 1386
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001207843082552052,
      "loss": 1.9511,
      "step": 1387
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012068138360526778,
      "loss": 2.0438,
      "step": 1388
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012057843606248953,
      "loss": 1.9865,
      "step": 1389
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012047546574082614,
      "loss": 2.0002,
      "step": 1390
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001203724727542586,
      "loss": 1.9154,
      "step": 1391
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012026945721679283,
      "loss": 1.9399,
      "step": 1392
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012016641924245987,
      "loss": 2.0533,
      "step": 1393
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0012006335894531553,
      "loss": 1.9953,
      "step": 1394
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0011996027643944025,
      "loss": 1.9712,
      "step": 1395
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0011985717183893923,
      "loss": 2.0011,
      "step": 1396
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0011975404525794197,
      "loss": 2.0834,
      "step": 1397
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0011965089681060235,
      "loss": 1.9319,
      "step": 1398
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0011954772661109852,
      "loss": 1.9598,
      "step": 1399
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0011944453477363264,
      "loss": 1.975,
      "step": 1400
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001193413214124308,
      "loss": 1.9437,
      "step": 1401
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011923808664174298,
      "loss": 2.0537,
      "step": 1402
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011913483057584284,
      "loss": 1.9711,
      "step": 1403
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011903155332902758,
      "loss": 2.0134,
      "step": 1404
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011892825501561783,
      "loss": 1.9182,
      "step": 1405
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011882493574995768,
      "loss": 2.0218,
      "step": 1406
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001187215956464142,
      "loss": 2.0552,
      "step": 1407
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011861823481937768,
      "loss": 2.0052,
      "step": 1408
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011851485338326131,
      "loss": 1.9477,
      "step": 1409
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011841145145250111,
      "loss": 2.0248,
      "step": 1410
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001183080291415557,
      "loss": 1.9217,
      "step": 1411
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011820458656490638,
      "loss": 1.9956,
      "step": 1412
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011810112383705681,
      "loss": 2.0064,
      "step": 1413
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011799764107253293,
      "loss": 1.9566,
      "step": 1414
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00117894138385883,
      "loss": 2.0471,
      "step": 1415
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001177906158916771,
      "loss": 1.9784,
      "step": 1416
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001176870737045075,
      "loss": 2.0043,
      "step": 1417
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011758351193898802,
      "loss": 1.9036,
      "step": 1418
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011747993070975438,
      "loss": 2.0428,
      "step": 1419
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011737633013146364,
      "loss": 1.9913,
      "step": 1420
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011727271031879444,
      "loss": 1.9987,
      "step": 1421
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011716907138644664,
      "loss": 2.0077,
      "step": 1422
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001170654134491412,
      "loss": 2.0187,
      "step": 1423
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011696173662162025,
      "loss": 1.9233,
      "step": 1424
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011685804101864677,
      "loss": 2.0219,
      "step": 1425
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011675432675500447,
      "loss": 2.0214,
      "step": 1426
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011665059394549773,
      "loss": 1.904,
      "step": 1427
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011654684270495162,
      "loss": 1.9755,
      "step": 1428
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001164430731482114,
      "loss": 1.9633,
      "step": 1429
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0011633928539014269,
      "loss": 2.0211,
      "step": 1430
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.001162354795456313,
      "loss": 1.9328,
      "step": 1431
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011613165572958298,
      "loss": 1.9341,
      "step": 1432
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011602781405692343,
      "loss": 2.0498,
      "step": 1433
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001159239546425981,
      "loss": 1.9738,
      "step": 1434
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00115820077601572,
      "loss": 1.9881,
      "step": 1435
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011571618304882984,
      "loss": 2.1258,
      "step": 1436
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011561227109937553,
      "loss": 1.9673,
      "step": 1437
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011550834186823237,
      "loss": 1.9841,
      "step": 1438
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011540439547044266,
      "loss": 2.038,
      "step": 1439
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001153004320210678,
      "loss": 1.9143,
      "step": 1440
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011519645163518806,
      "loss": 1.9961,
      "step": 1441
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011509245442790238,
      "loss": 2.0483,
      "step": 1442
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001149884405143284,
      "loss": 1.9781,
      "step": 1443
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011488441000960226,
      "loss": 2.0336,
      "step": 1444
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011478036302887836,
      "loss": 1.9546,
      "step": 1445
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011467629968732946,
      "loss": 1.9828,
      "step": 1446
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011457222010014638,
      "loss": 1.933,
      "step": 1447
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011446812438253788,
      "loss": 1.9919,
      "step": 1448
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011436401264973066,
      "loss": 1.9725,
      "step": 1449
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001142598850169691,
      "loss": 1.9327,
      "step": 1450
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011415574159951516,
      "loss": 2.0204,
      "step": 1451
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011405158251264831,
      "loss": 1.9923,
      "step": 1452
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011394740787166538,
      "loss": 1.9641,
      "step": 1453
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011384321779188034,
      "loss": 2.0454,
      "step": 1454
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001137390123886243,
      "loss": 1.9596,
      "step": 1455
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011363479177724537,
      "loss": 1.9667,
      "step": 1456
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011353055607310845,
      "loss": 2.0499,
      "step": 1457
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001134263053915951,
      "loss": 2.0997,
      "step": 1458
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011332203984810362,
      "loss": 1.9242,
      "step": 1459
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011321775955804854,
      "loss": 1.9777,
      "step": 1460
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011311346463686088,
      "loss": 2.0677,
      "step": 1461
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0011300915519998778,
      "loss": 1.9902,
      "step": 1462
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001129048313628925,
      "loss": 1.9275,
      "step": 1463
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001128004932410542,
      "loss": 1.9599,
      "step": 1464
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001126961409499678,
      "loss": 1.9988,
      "step": 1465
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011259177460514408,
      "loss": 1.9869,
      "step": 1466
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011248739432210917,
      "loss": 2.0322,
      "step": 1467
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011238300021640475,
      "loss": 1.9729,
      "step": 1468
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011227859240358778,
      "loss": 1.9967,
      "step": 1469
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011217417099923038,
      "loss": 1.9835,
      "step": 1470
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011206973611891967,
      "loss": 2.0131,
      "step": 1471
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011196528787825782,
      "loss": 2.0445,
      "step": 1472
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011186082639286167,
      "loss": 1.9923,
      "step": 1473
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011175635177836274,
      "loss": 1.9708,
      "step": 1474
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011165186415040714,
      "loss": 2.0711,
      "step": 1475
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011154736362465527,
      "loss": 2.0144,
      "step": 1476
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011144285031678197,
      "loss": 2.0364,
      "step": 1477
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011133832434247607,
      "loss": 1.9648,
      "step": 1478
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011123378581744054,
      "loss": 1.9815,
      "step": 1479
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011112923485739217,
      "loss": 1.9404,
      "step": 1480
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011102467157806156,
      "loss": 1.9733,
      "step": 1481
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011092009609519288,
      "loss": 1.9713,
      "step": 1482
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011081550852454387,
      "loss": 1.9535,
      "step": 1483
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011071090898188566,
      "loss": 2.0495,
      "step": 1484
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001106062975830026,
      "loss": 1.9729,
      "step": 1485
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011050167444369215,
      "loss": 1.9804,
      "step": 1486
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011039703967976478,
      "loss": 2.024,
      "step": 1487
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011029239340704384,
      "loss": 2.0717,
      "step": 1488
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011018773574136545,
      "loss": 2.0129,
      "step": 1489
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0011008306679857827,
      "loss": 1.9889,
      "step": 1490
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001099783866945435,
      "loss": 1.985,
      "step": 1491
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0010987369554513462,
      "loss": 2.0752,
      "step": 1492
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0010976899346623744,
      "loss": 1.9381,
      "step": 1493
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010966428057374979,
      "loss": 1.9904,
      "step": 1494
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001095595569835815,
      "loss": 2.0128,
      "step": 1495
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010945482281165427,
      "loss": 1.9579,
      "step": 1496
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010935007817390145,
      "loss": 2.0238,
      "step": 1497
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010924532318626798,
      "loss": 1.8935,
      "step": 1498
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010914055796471035,
      "loss": 2.0481,
      "step": 1499
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010903578262519626,
      "loss": 1.9333,
      "step": 1500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010893099728370465,
      "loss": 1.9122,
      "step": 1501
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010882620205622559,
      "loss": 1.9202,
      "step": 1502
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010872139705876002,
      "loss": 1.9836,
      "step": 1503
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001086165824073197,
      "loss": 2.0492,
      "step": 1504
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010851175821792714,
      "loss": 2.0268,
      "step": 1505
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010840692460661536,
      "loss": 1.981,
      "step": 1506
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010830208168942778,
      "loss": 1.9633,
      "step": 1507
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010819722958241816,
      "loss": 1.971,
      "step": 1508
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010809236840165042,
      "loss": 2.0367,
      "step": 1509
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001079874982631986,
      "loss": 2.0085,
      "step": 1510
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001078826192831465,
      "loss": 2.0053,
      "step": 1511
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010777773157758784,
      "loss": 1.9646,
      "step": 1512
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010767283526262595,
      "loss": 1.9678,
      "step": 1513
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010756793045437365,
      "loss": 2.031,
      "step": 1514
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010746301726895324,
      "loss": 2.0045,
      "step": 1515
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001073580958224963,
      "loss": 1.986,
      "step": 1516
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010725316623114343,
      "loss": 1.9799,
      "step": 1517
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010714822861104432,
      "loss": 1.9548,
      "step": 1518
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010704328307835765,
      "loss": 1.9639,
      "step": 1519
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.001069383297492507,
      "loss": 1.9937,
      "step": 1520
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010683336873989941,
      "loss": 1.9835,
      "step": 1521
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010672840016648834,
      "loss": 2.012,
      "step": 1522
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010662342414521028,
      "loss": 2.0561,
      "step": 1523
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0010651844079226631,
      "loss": 1.9337,
      "step": 1524
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010641345022386571,
      "loss": 1.9762,
      "step": 1525
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010630845255622556,
      "loss": 1.9506,
      "step": 1526
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010620344790557101,
      "loss": 1.9668,
      "step": 1527
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010609843638813479,
      "loss": 1.9873,
      "step": 1528
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010599341812015733,
      "loss": 2.0113,
      "step": 1529
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010588839321788643,
      "loss": 2.0119,
      "step": 1530
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010578336179757732,
      "loss": 2.0328,
      "step": 1531
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010567832397549242,
      "loss": 1.9681,
      "step": 1532
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001055732798679012,
      "loss": 1.9323,
      "step": 1533
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010546822959108016,
      "loss": 2.0237,
      "step": 1534
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010536317326131255,
      "loss": 2.0133,
      "step": 1535
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010525811099488837,
      "loss": 1.9234,
      "step": 1536
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001051530429081042,
      "loss": 1.9643,
      "step": 1537
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010504796911726302,
      "loss": 2.0206,
      "step": 1538
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010494288973867411,
      "loss": 1.96,
      "step": 1539
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010483780488865304,
      "loss": 1.9971,
      "step": 1540
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010473271468352137,
      "loss": 2.0204,
      "step": 1541
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001046276192396065,
      "loss": 2.0258,
      "step": 1542
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010452251867324176,
      "loss": 1.9346,
      "step": 1543
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010441741310076615,
      "loss": 2.015,
      "step": 1544
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001043123026385241,
      "loss": 1.9739,
      "step": 1545
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010420718740286555,
      "loss": 2.0023,
      "step": 1546
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010410206751014566,
      "loss": 2.0228,
      "step": 1547
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010399694307672482,
      "loss": 1.9363,
      "step": 1548
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010389181421896839,
      "loss": 1.9665,
      "step": 1549
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010378668105324662,
      "loss": 1.926,
      "step": 1550
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010368154369593456,
      "loss": 1.989,
      "step": 1551
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010357640226341192,
      "loss": 1.9684,
      "step": 1552
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010347125687206287,
      "loss": 1.9626,
      "step": 1553
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0010336610763827594,
      "loss": 1.9729,
      "step": 1554
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010326095467844399,
      "loss": 1.9802,
      "step": 1555
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010315579810896399,
      "loss": 2.0125,
      "step": 1556
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010305063804623687,
      "loss": 1.9968,
      "step": 1557
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010294547460666743,
      "loss": 2.0094,
      "step": 1558
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010284030790666421,
      "loss": 1.9932,
      "step": 1559
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010273513806263943,
      "loss": 1.9948,
      "step": 1560
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010262996519100867,
      "loss": 1.9315,
      "step": 1561
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010252478940819092,
      "loss": 1.9959,
      "step": 1562
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010241961083060844,
      "loss": 2.0812,
      "step": 1563
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010231442957468646,
      "loss": 1.936,
      "step": 1564
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010220924575685332,
      "loss": 1.9334,
      "step": 1565
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010210405949354015,
      "loss": 2.0743,
      "step": 1566
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.001019988709011807,
      "loss": 1.9782,
      "step": 1567
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010189368009621137,
      "loss": 2.0199,
      "step": 1568
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010178848719507106,
      "loss": 1.926,
      "step": 1569
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010168329231420084,
      "loss": 2.001,
      "step": 1570
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.001015780955700441,
      "loss": 1.9569,
      "step": 1571
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010147289707904635,
      "loss": 2.0103,
      "step": 1572
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.001013676969576548,
      "loss": 2.0018,
      "step": 1573
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010126249532231865,
      "loss": 1.9848,
      "step": 1574
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010115729228948878,
      "loss": 1.9725,
      "step": 1575
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010105208797561755,
      "loss": 2.0296,
      "step": 1576
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010094688249715866,
      "loss": 1.9522,
      "step": 1577
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010084167597056732,
      "loss": 1.9606,
      "step": 1578
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010073646851229971,
      "loss": 2.003,
      "step": 1579
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010063126023881312,
      "loss": 1.9781,
      "step": 1580
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010052605126656573,
      "loss": 1.9846,
      "step": 1581
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010042084171201654,
      "loss": 1.9346,
      "step": 1582
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010031563169162502,
      "loss": 2.0157,
      "step": 1583
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.001002104213218514,
      "loss": 1.9656,
      "step": 1584
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0010010521071915617,
      "loss": 2.0394,
      "step": 1585
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.001,
      "loss": 2.1115,
      "step": 1586
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009989478928084385,
      "loss": 2.0265,
      "step": 1587
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000997895786781486,
      "loss": 1.9647,
      "step": 1588
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009968436830837498,
      "loss": 1.9512,
      "step": 1589
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009957915828798349,
      "loss": 1.9189,
      "step": 1590
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009947394873343427,
      "loss": 1.9728,
      "step": 1591
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009936873976118688,
      "loss": 2.0013,
      "step": 1592
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000992635314877003,
      "loss": 1.9386,
      "step": 1593
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009915832402943268,
      "loss": 2.0413,
      "step": 1594
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009905311750284136,
      "loss": 2.0455,
      "step": 1595
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009894791202438252,
      "loss": 1.9944,
      "step": 1596
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009884270771051125,
      "loss": 1.9801,
      "step": 1597
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009873750467768137,
      "loss": 1.9845,
      "step": 1598
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009863230304234525,
      "loss": 1.9974,
      "step": 1599
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000985271029209537,
      "loss": 1.9149,
      "step": 1600
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009842190442995592,
      "loss": 2.0311,
      "step": 1601
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009831670768579916,
      "loss": 1.9615,
      "step": 1602
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009821151280492897,
      "loss": 2.0104,
      "step": 1603
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009810631990378861,
      "loss": 1.9678,
      "step": 1604
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000980011290988193,
      "loss": 1.9849,
      "step": 1605
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009789594050645986,
      "loss": 1.9993,
      "step": 1606
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009779075424314666,
      "loss": 1.9363,
      "step": 1607
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009768557042531354,
      "loss": 2.016,
      "step": 1608
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009758038916939157,
      "loss": 2.0202,
      "step": 1609
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000974752105918091,
      "loss": 1.904,
      "step": 1610
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009737003480899136,
      "loss": 1.9898,
      "step": 1611
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009726486193736058,
      "loss": 2.024,
      "step": 1612
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009715969209333579,
      "loss": 1.9486,
      "step": 1613
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009705452539333259,
      "loss": 1.9851,
      "step": 1614
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009694936195376314,
      "loss": 1.9982,
      "step": 1615
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009684420189103603,
      "loss": 1.9514,
      "step": 1616
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009673904532155602,
      "loss": 1.9297,
      "step": 1617
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009663389236172407,
      "loss": 1.9525,
      "step": 1618
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009652874312793716,
      "loss": 2.0181,
      "step": 1619
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000964235977365881,
      "loss": 1.9276,
      "step": 1620
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009631845630406544,
      "loss": 2.0593,
      "step": 1621
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009621331894675339,
      "loss": 1.9457,
      "step": 1622
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009610818578103164,
      "loss": 1.9651,
      "step": 1623
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000960030569232752,
      "loss": 1.9265,
      "step": 1624
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009589793248985436,
      "loss": 1.9734,
      "step": 1625
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009579281259713449,
      "loss": 1.9525,
      "step": 1626
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009568769736147593,
      "loss": 2.0336,
      "step": 1627
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009558258689923388,
      "loss": 1.9424,
      "step": 1628
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009547748132675826,
      "loss": 2.0631,
      "step": 1629
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009537238076039354,
      "loss": 2.0071,
      "step": 1630
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009526728531647868,
      "loss": 1.9346,
      "step": 1631
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009516219511134695,
      "loss": 2.0024,
      "step": 1632
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009505711026132586,
      "loss": 2.0097,
      "step": 1633
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009495203088273698,
      "loss": 2.034,
      "step": 1634
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009484695709189581,
      "loss": 1.9967,
      "step": 1635
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009474188900511163,
      "loss": 1.9834,
      "step": 1636
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009463682673868744,
      "loss": 1.9937,
      "step": 1637
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009453177040891986,
      "loss": 2.0226,
      "step": 1638
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009442672013209881,
      "loss": 1.9485,
      "step": 1639
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009432167602450759,
      "loss": 1.9673,
      "step": 1640
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000942166382024227,
      "loss": 1.9638,
      "step": 1641
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000941116067821136,
      "loss": 2.0197,
      "step": 1642
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009400658187984269,
      "loss": 1.8942,
      "step": 1643
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009390156361186523,
      "loss": 1.9804,
      "step": 1644
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009379655209442901,
      "loss": 1.9793,
      "step": 1645
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009369154744377445,
      "loss": 2.0104,
      "step": 1646
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009358654977613432,
      "loss": 2.0287,
      "step": 1647
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000934815592077337,
      "loss": 2.0093,
      "step": 1648
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009337657585478974,
      "loss": 1.9822,
      "step": 1649
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009327159983351167,
      "loss": 2.0142,
      "step": 1650
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000931666312601006,
      "loss": 1.8852,
      "step": 1651
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009306167025074933,
      "loss": 1.9687,
      "step": 1652
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009295671692164237,
      "loss": 1.9465,
      "step": 1653
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000928517713889557,
      "loss": 1.9656,
      "step": 1654
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009274683376885662,
      "loss": 1.9282,
      "step": 1655
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009264190417750375,
      "loss": 1.9892,
      "step": 1656
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009253698273104676,
      "loss": 1.9753,
      "step": 1657
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009243206954562638,
      "loss": 2.0136,
      "step": 1658
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000923271647373741,
      "loss": 1.97,
      "step": 1659
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009222226842241219,
      "loss": 2.0307,
      "step": 1660
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009211738071685354,
      "loss": 1.9554,
      "step": 1661
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009201250173680145,
      "loss": 2.0446,
      "step": 1662
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009190763159834956,
      "loss": 1.9999,
      "step": 1663
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009180277041758185,
      "loss": 1.9338,
      "step": 1664
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009169791831057223,
      "loss": 1.9689,
      "step": 1665
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009159307539338466,
      "loss": 1.9873,
      "step": 1666
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009148824178207284,
      "loss": 1.9856,
      "step": 1667
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009138341759268028,
      "loss": 1.939,
      "step": 1668
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009127860294124,
      "loss": 1.9604,
      "step": 1669
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009117379794377443,
      "loss": 1.993,
      "step": 1670
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009106900271629536,
      "loss": 1.9469,
      "step": 1671
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009096421737480376,
      "loss": 1.9814,
      "step": 1672
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009085944203528968,
      "loss": 1.9983,
      "step": 1673
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009075467681373202,
      "loss": 2.0085,
      "step": 1674
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009064992182609857,
      "loss": 1.9776,
      "step": 1675
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009054517718834575,
      "loss": 1.97,
      "step": 1676
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009044044301641849,
      "loss": 1.9797,
      "step": 1677
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009033571942625022,
      "loss": 1.967,
      "step": 1678
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000902310065337626,
      "loss": 1.9823,
      "step": 1679
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0009012630445486541,
      "loss": 1.9771,
      "step": 1680
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0009002161330545653,
      "loss": 2.0161,
      "step": 1681
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008991693320142176,
      "loss": 1.9691,
      "step": 1682
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008981226425863457,
      "loss": 1.9369,
      "step": 1683
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008970760659295616,
      "loss": 2.0251,
      "step": 1684
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008960296032023523,
      "loss": 1.9637,
      "step": 1685
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008949832555630791,
      "loss": 1.9951,
      "step": 1686
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008939370241699743,
      "loss": 1.924,
      "step": 1687
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008928909101811437,
      "loss": 2.0118,
      "step": 1688
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008918449147545616,
      "loss": 1.9914,
      "step": 1689
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008907990390480716,
      "loss": 1.9667,
      "step": 1690
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008897532842193849,
      "loss": 1.9452,
      "step": 1691
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008887076514260786,
      "loss": 1.9628,
      "step": 1692
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008876621418255945,
      "loss": 2.007,
      "step": 1693
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008866167565752392,
      "loss": 1.9892,
      "step": 1694
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008855714968321803,
      "loss": 1.9835,
      "step": 1695
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008845263637534471,
      "loss": 1.9784,
      "step": 1696
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008834813584959289,
      "loss": 2.0278,
      "step": 1697
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008824364822163726,
      "loss": 2.0235,
      "step": 1698
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008813917360713833,
      "loss": 1.98,
      "step": 1699
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008803471212174217,
      "loss": 1.9704,
      "step": 1700
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008793026388108033,
      "loss": 1.933,
      "step": 1701
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008782582900076965,
      "loss": 1.9212,
      "step": 1702
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008772140759641224,
      "loss": 2.0121,
      "step": 1703
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008761699978359527,
      "loss": 1.9687,
      "step": 1704
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008751260567789086,
      "loss": 1.9705,
      "step": 1705
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008740822539485593,
      "loss": 2.0596,
      "step": 1706
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000873038590500322,
      "loss": 1.8859,
      "step": 1707
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008719950675894583,
      "loss": 1.9996,
      "step": 1708
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000870951686371075,
      "loss": 2.029,
      "step": 1709
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008699084480001223,
      "loss": 2.0221,
      "step": 1710
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008688653536313914,
      "loss": 1.9635,
      "step": 1711
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008678224044195148,
      "loss": 1.9739,
      "step": 1712
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000866779601518964,
      "loss": 1.9892,
      "step": 1713
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000865736946084049,
      "loss": 1.999,
      "step": 1714
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008646944392689158,
      "loss": 2.0473,
      "step": 1715
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008636520822275464,
      "loss": 1.9934,
      "step": 1716
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008626098761137572,
      "loss": 2.0001,
      "step": 1717
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008615678220811971,
      "loss": 2.0263,
      "step": 1718
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008605259212833466,
      "loss": 1.9561,
      "step": 1719
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008594841748735171,
      "loss": 1.9826,
      "step": 1720
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008584425840048487,
      "loss": 1.9698,
      "step": 1721
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008574011498303092,
      "loss": 1.9259,
      "step": 1722
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008563598735026934,
      "loss": 2.0179,
      "step": 1723
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000855318756174621,
      "loss": 2.0285,
      "step": 1724
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008542777989985364,
      "loss": 2.0327,
      "step": 1725
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008532370031267053,
      "loss": 1.9617,
      "step": 1726
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008521963697112162,
      "loss": 2.0022,
      "step": 1727
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008511558999039774,
      "loss": 2.0173,
      "step": 1728
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000850115594856716,
      "loss": 1.9174,
      "step": 1729
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008490754557209762,
      "loss": 2.0466,
      "step": 1730
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008480354836481194,
      "loss": 1.9969,
      "step": 1731
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008469956797893221,
      "loss": 1.9836,
      "step": 1732
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008459560452955734,
      "loss": 1.9434,
      "step": 1733
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008449165813176764,
      "loss": 2.0549,
      "step": 1734
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008438772890062448,
      "loss": 1.9915,
      "step": 1735
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008428381695117018,
      "loss": 1.8869,
      "step": 1736
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00084179922398428,
      "loss": 1.8743,
      "step": 1737
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008407604535740195,
      "loss": 2.0145,
      "step": 1738
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0008397218594307661,
      "loss": 1.9042,
      "step": 1739
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008386834427041704,
      "loss": 1.9218,
      "step": 1740
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000837645204543687,
      "loss": 1.9682,
      "step": 1741
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008366071460985733,
      "loss": 1.8635,
      "step": 1742
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008355692685178862,
      "loss": 1.9915,
      "step": 1743
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008345315729504838,
      "loss": 1.9664,
      "step": 1744
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008334940605450228,
      "loss": 1.9627,
      "step": 1745
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008324567324499559,
      "loss": 1.9971,
      "step": 1746
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008314195898135328,
      "loss": 1.9748,
      "step": 1747
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008303826337837979,
      "loss": 1.9482,
      "step": 1748
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008293458655085884,
      "loss": 2.0236,
      "step": 1749
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000828309286135534,
      "loss": 1.9953,
      "step": 1750
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008272728968120557,
      "loss": 1.973,
      "step": 1751
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008262366986853637,
      "loss": 2.0457,
      "step": 1752
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008252006929024565,
      "loss": 1.9848,
      "step": 1753
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008241648806101196,
      "loss": 1.9285,
      "step": 1754
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008231292629549252,
      "loss": 1.9616,
      "step": 1755
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008220938410832289,
      "loss": 2.1081,
      "step": 1756
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008210586161411704,
      "loss": 1.9339,
      "step": 1757
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008200235892746705,
      "loss": 2.0079,
      "step": 1758
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000818988761629432,
      "loss": 2.001,
      "step": 1759
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008179541343509365,
      "loss": 2.0024,
      "step": 1760
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008169197085844431,
      "loss": 1.9783,
      "step": 1761
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008158854854749891,
      "loss": 2.0527,
      "step": 1762
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000814851466167387,
      "loss": 1.9876,
      "step": 1763
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008138176518062234,
      "loss": 2.0189,
      "step": 1764
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008127840435358582,
      "loss": 1.9691,
      "step": 1765
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008117506425004234,
      "loss": 2.0089,
      "step": 1766
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008107174498438217,
      "loss": 2.0181,
      "step": 1767
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008096844667097244,
      "loss": 2.0392,
      "step": 1768
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008086516942415716,
      "loss": 2.0529,
      "step": 1769
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0008076191335825702,
      "loss": 1.9907,
      "step": 1770
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000806586785875692,
      "loss": 1.9291,
      "step": 1771
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0008055546522636736,
      "loss": 1.9969,
      "step": 1772
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000804522733889015,
      "loss": 1.9671,
      "step": 1773
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0008034910318939766,
      "loss": 1.9188,
      "step": 1774
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0008024595474205807,
      "loss": 1.9888,
      "step": 1775
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000801428281610608,
      "loss": 1.9667,
      "step": 1776
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0008003972356055977,
      "loss": 1.955,
      "step": 1777
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007993664105468452,
      "loss": 1.9612,
      "step": 1778
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007983358075754015,
      "loss": 1.9994,
      "step": 1779
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000797305427832072,
      "loss": 1.995,
      "step": 1780
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007962752724574144,
      "loss": 1.9729,
      "step": 1781
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007952453425917386,
      "loss": 1.9578,
      "step": 1782
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007942156393751052,
      "loss": 2.0136,
      "step": 1783
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007931861639473226,
      "loss": 1.9178,
      "step": 1784
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007921569174479481,
      "loss": 1.9162,
      "step": 1785
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000791127901016286,
      "loss": 2.0047,
      "step": 1786
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007900991157913846,
      "loss": 1.9636,
      "step": 1787
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007890705629120375,
      "loss": 2.0034,
      "step": 1788
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007880422435167801,
      "loss": 1.929,
      "step": 1789
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00078701415874389,
      "loss": 1.8884,
      "step": 1790
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007859863097313851,
      "loss": 2.0243,
      "step": 1791
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007849586976170222,
      "loss": 1.9691,
      "step": 1792
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007839313235382954,
      "loss": 1.9572,
      "step": 1793
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007829041886324359,
      "loss": 1.9209,
      "step": 1794
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007818772940364105,
      "loss": 1.9938,
      "step": 1795
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007808506408869187,
      "loss": 1.9695,
      "step": 1796
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007798242303203939,
      "loss": 1.9271,
      "step": 1797
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007787980634730007,
      "loss": 2.0286,
      "step": 1798
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007777721414806333,
      "loss": 1.9787,
      "step": 1799
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007767464654789161,
      "loss": 2.0081,
      "step": 1800
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007757210366032001,
      "loss": 1.9589,
      "step": 1801
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000774695855988563,
      "loss": 1.9344,
      "step": 1802
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007736709247698079,
      "loss": 2.0335,
      "step": 1803
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000772646244081462,
      "loss": 1.9429,
      "step": 1804
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000771621815057775,
      "loss": 2.0139,
      "step": 1805
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007705976388327173,
      "loss": 1.9585,
      "step": 1806
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007695737165399807,
      "loss": 1.9613,
      "step": 1807
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007685500493129755,
      "loss": 1.9306,
      "step": 1808
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007675266382848289,
      "loss": 2.0499,
      "step": 1809
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007665034845883856,
      "loss": 1.8765,
      "step": 1810
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007654805893562049,
      "loss": 1.9346,
      "step": 1811
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007644579537205598,
      "loss": 1.9605,
      "step": 1812
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007634355788134364,
      "loss": 1.9722,
      "step": 1813
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000762413465766532,
      "loss": 1.9239,
      "step": 1814
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007613916157112537,
      "loss": 1.9108,
      "step": 1815
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007603700297787187,
      "loss": 1.9092,
      "step": 1816
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007593487090997501,
      "loss": 2.0477,
      "step": 1817
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007583276548048788,
      "loss": 1.9884,
      "step": 1818
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007573068680243399,
      "loss": 1.9824,
      "step": 1819
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000756286349888073,
      "loss": 1.9528,
      "step": 1820
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00075526610152572,
      "loss": 1.9898,
      "step": 1821
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000754246124066624,
      "loss": 1.8995,
      "step": 1822
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007532264186398293,
      "loss": 1.9548,
      "step": 1823
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007522069863740771,
      "loss": 1.9914,
      "step": 1824
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007511878283978082,
      "loss": 1.9912,
      "step": 1825
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007501689458391591,
      "loss": 1.9875,
      "step": 1826
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007491503398259607,
      "loss": 1.931,
      "step": 1827
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007481320114857388,
      "loss": 1.9449,
      "step": 1828
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007471139619457112,
      "loss": 1.979,
      "step": 1829
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007460961923327878,
      "loss": 1.9493,
      "step": 1830
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007450787037735677,
      "loss": 2.0071,
      "step": 1831
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007440614973943393,
      "loss": 2.0383,
      "step": 1832
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007430445743210794,
      "loss": 1.9463,
      "step": 1833
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007420279356794497,
      "loss": 1.9887,
      "step": 1834
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007410115825947981,
      "loss": 1.9817,
      "step": 1835
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007399955161921564,
      "loss": 2.0475,
      "step": 1836
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007389797375962386,
      "loss": 1.9644,
      "step": 1837
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007379642479314404,
      "loss": 1.9929,
      "step": 1838
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007369490483218377,
      "loss": 1.9816,
      "step": 1839
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000735934139891185,
      "loss": 1.89,
      "step": 1840
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007349195237629151,
      "loss": 1.99,
      "step": 1841
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007339052010601365,
      "loss": 1.8957,
      "step": 1842
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007328911729056338,
      "loss": 2.0506,
      "step": 1843
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007318774404218645,
      "loss": 1.954,
      "step": 1844
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007308640047309591,
      "loss": 1.9688,
      "step": 1845
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007298508669547208,
      "loss": 1.9913,
      "step": 1846
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007288380282146213,
      "loss": 1.967,
      "step": 1847
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007278254896318026,
      "loss": 1.9979,
      "step": 1848
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007268132523270732,
      "loss": 1.9144,
      "step": 1849
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007258013174209092,
      "loss": 2.0022,
      "step": 1850
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007247896860334515,
      "loss": 1.9511,
      "step": 1851
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000723778359284505,
      "loss": 1.9859,
      "step": 1852
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007227673382935376,
      "loss": 1.9202,
      "step": 1853
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007217566241796785,
      "loss": 1.9959,
      "step": 1854
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007207462180617172,
      "loss": 1.9857,
      "step": 1855
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007197361210581026,
      "loss": 2.0757,
      "step": 1856
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007187263342869412,
      "loss": 1.9412,
      "step": 1857
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007177168588659961,
      "loss": 1.9479,
      "step": 1858
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007167076959126857,
      "loss": 2.0021,
      "step": 1859
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007156988465440825,
      "loss": 1.9694,
      "step": 1860
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007146903118769126,
      "loss": 2.0025,
      "step": 1861
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007136820930275522,
      "loss": 1.929,
      "step": 1862
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0007126741911120294,
      "loss": 2.0295,
      "step": 1863
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000711666607246021,
      "loss": 1.9505,
      "step": 1864
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0007106593425448512,
      "loss": 1.9346,
      "step": 1865
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0007096523981234917,
      "loss": 2.005,
      "step": 1866
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0007086457750965591,
      "loss": 2.0177,
      "step": 1867
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000707639474578315,
      "loss": 1.9959,
      "step": 1868
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0007066334976826629,
      "loss": 1.9343,
      "step": 1869
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0007056278455231488,
      "loss": 1.9856,
      "step": 1870
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0007046225192129595,
      "loss": 1.9548,
      "step": 1871
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00070361751986492,
      "loss": 1.9328,
      "step": 1872
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0007026128485914946,
      "loss": 1.8947,
      "step": 1873
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0007016085065047839,
      "loss": 1.9552,
      "step": 1874
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0007006044947165238,
      "loss": 2.0229,
      "step": 1875
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006996008143380848,
      "loss": 1.9534,
      "step": 1876
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006985974664804712,
      "loss": 1.9784,
      "step": 1877
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006975944522543187,
      "loss": 1.9063,
      "step": 1878
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006965917727698934,
      "loss": 2.0572,
      "step": 1879
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006955894291370912,
      "loss": 2.0055,
      "step": 1880
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006945874224654361,
      "loss": 1.9697,
      "step": 1881
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006935857538640793,
      "loss": 1.9551,
      "step": 1882
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006925844244417978,
      "loss": 2.0453,
      "step": 1883
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006915834353069928,
      "loss": 2.0172,
      "step": 1884
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006905827875676891,
      "loss": 2.0414,
      "step": 1885
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006895824823315338,
      "loss": 2.0015,
      "step": 1886
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006885825207057942,
      "loss": 1.9625,
      "step": 1887
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006875829037973579,
      "loss": 2.0789,
      "step": 1888
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006865836327127308,
      "loss": 1.9478,
      "step": 1889
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006855847085580356,
      "loss": 2.0178,
      "step": 1890
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006845861324390116,
      "loss": 1.9612,
      "step": 1891
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006835879054610123,
      "loss": 2.0498,
      "step": 1892
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000682590028729005,
      "loss": 1.9245,
      "step": 1893
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006815925033475692,
      "loss": 1.9177,
      "step": 1894
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006805953304208954,
      "loss": 1.9323,
      "step": 1895
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006795985110527845,
      "loss": 1.9406,
      "step": 1896
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006786020463466451,
      "loss": 1.9764,
      "step": 1897
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000677605937405494,
      "loss": 1.98,
      "step": 1898
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006766101853319542,
      "loss": 1.9083,
      "step": 1899
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006756147912282527,
      "loss": 1.934,
      "step": 1900
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006746197561962213,
      "loss": 2.0014,
      "step": 1901
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006736250813372944,
      "loss": 1.9195,
      "step": 1902
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006726307677525066,
      "loss": 2.0019,
      "step": 1903
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006716368165424933,
      "loss": 1.9826,
      "step": 1904
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006706432288074895,
      "loss": 1.9464,
      "step": 1905
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006696500056473261,
      "loss": 1.9775,
      "step": 1906
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006686571481614326,
      "loss": 1.9764,
      "step": 1907
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006676646574488317,
      "loss": 1.9529,
      "step": 1908
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006666725346081413,
      "loss": 2.0103,
      "step": 1909
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006656807807375718,
      "loss": 1.9286,
      "step": 1910
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006646893969349253,
      "loss": 2.0195,
      "step": 1911
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006636983842975939,
      "loss": 2.0011,
      "step": 1912
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006627077439225591,
      "loss": 1.9679,
      "step": 1913
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006617174769063905,
      "loss": 2.0344,
      "step": 1914
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006607275843452439,
      "loss": 2.0023,
      "step": 1915
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006597380673348611,
      "loss": 2.06,
      "step": 1916
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006587489269705682,
      "loss": 1.934,
      "step": 1917
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006577601643472737,
      "loss": 1.9861,
      "step": 1918
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006567717805594688,
      "loss": 1.9286,
      "step": 1919
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006557837767012252,
      "loss": 1.9544,
      "step": 1920
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006547961538661935,
      "loss": 1.9427,
      "step": 1921
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006538089131476029,
      "loss": 2.0148,
      "step": 1922
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006528220556382598,
      "loss": 2.011,
      "step": 1923
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006518355824305463,
      "loss": 1.9691,
      "step": 1924
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006508494946164188,
      "loss": 1.9386,
      "step": 1925
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006498637932874074,
      "loss": 2.0333,
      "step": 1926
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006488784795346147,
      "loss": 1.9429,
      "step": 1927
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006478935544487133,
      "loss": 1.874,
      "step": 1928
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006469090191199464,
      "loss": 2.0387,
      "step": 1929
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006459248746381259,
      "loss": 2.0645,
      "step": 1930
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006449411220926301,
      "loss": 1.9916,
      "step": 1931
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006439577625724044,
      "loss": 2.0048,
      "step": 1932
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006429747971659587,
      "loss": 1.9118,
      "step": 1933
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006419922269613672,
      "loss": 1.9683,
      "step": 1934
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006410100530462654,
      "loss": 1.9608,
      "step": 1935
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006400282765078514,
      "loss": 1.9116,
      "step": 1936
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006390468984328828,
      "loss": 1.9739,
      "step": 1937
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006380659199076763,
      "loss": 2.0504,
      "step": 1938
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006370853420181069,
      "loss": 2.0353,
      "step": 1939
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006361051658496045,
      "loss": 1.9374,
      "step": 1940
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006351253924871561,
      "loss": 1.9498,
      "step": 1941
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006341460230153019,
      "loss": 2.0407,
      "step": 1942
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006331670585181349,
      "loss": 1.9505,
      "step": 1943
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006321885000793006,
      "loss": 1.909,
      "step": 1944
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006312103487819943,
      "loss": 1.9952,
      "step": 1945
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006302326057089606,
      "loss": 1.9768,
      "step": 1946
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000629255271942493,
      "loss": 1.9929,
      "step": 1947
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006282783485644312,
      "loss": 2.1206,
      "step": 1948
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006273018366561609,
      "loss": 1.9114,
      "step": 1949
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006263257372986122,
      "loss": 1.9661,
      "step": 1950
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006253500515722585,
      "loss": 1.9564,
      "step": 1951
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006243747805571158,
      "loss": 1.9813,
      "step": 1952
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006233999253327403,
      "loss": 2.0061,
      "step": 1953
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006224254869782285,
      "loss": 2.0107,
      "step": 1954
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006214514665722156,
      "loss": 1.9915,
      "step": 1955
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006204778651928733,
      "loss": 1.9369,
      "step": 1956
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006195046839179105,
      "loss": 1.9516,
      "step": 1957
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006185319238245705,
      "loss": 2.0036,
      "step": 1958
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006175595859896301,
      "loss": 1.924,
      "step": 1959
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006165876714893995,
      "loss": 1.9906,
      "step": 1960
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006156161813997197,
      "loss": 2.0461,
      "step": 1961
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006146451167959625,
      "loss": 1.942,
      "step": 1962
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006136744787530275,
      "loss": 1.9873,
      "step": 1963
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006127042683453434,
      "loss": 2.0403,
      "step": 1964
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006117344866468652,
      "loss": 1.9754,
      "step": 1965
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000610765134731073,
      "loss": 1.9962,
      "step": 1966
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006097962136709709,
      "loss": 1.9959,
      "step": 1967
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006088277245390874,
      "loss": 1.9715,
      "step": 1968
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006078596684074715,
      "loss": 2.0092,
      "step": 1969
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000606892046347694,
      "loss": 1.9923,
      "step": 1970
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006059248594308439,
      "loss": 2.0592,
      "step": 1971
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006049581087275295,
      "loss": 1.9615,
      "step": 1972
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006039917953078764,
      "loss": 2.0036,
      "step": 1973
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006030259202415253,
      "loss": 1.953,
      "step": 1974
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006020604845976323,
      "loss": 2.0293,
      "step": 1975
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000601095489444867,
      "loss": 1.9422,
      "step": 1976
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006001309358514113,
      "loss": 1.9994,
      "step": 1977
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005991668248849582,
      "loss": 1.9715,
      "step": 1978
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005982031576127111,
      "loss": 1.9922,
      "step": 1979
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005972399351013822,
      "loss": 1.9757,
      "step": 1980
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005962771584171909,
      "loss": 1.997,
      "step": 1981
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005953148286258635,
      "loss": 1.9769,
      "step": 1982
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000594352946792632,
      "loss": 1.9745,
      "step": 1983
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005933915139822314,
      "loss": 1.9556,
      "step": 1984
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005924305312589011,
      "loss": 2.0122,
      "step": 1985
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000591469999686381,
      "loss": 1.9885,
      "step": 1986
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005905099203279127,
      "loss": 1.9786,
      "step": 1987
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005895502942462361,
      "loss": 1.978,
      "step": 1988
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005885911225035904,
      "loss": 1.9825,
      "step": 1989
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005876324061617113,
      "loss": 2.0069,
      "step": 1990
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005866741462818304,
      "loss": 2.028,
      "step": 1991
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005857163439246745,
      "loss": 2.0266,
      "step": 1992
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005847590001504632,
      "loss": 1.9267,
      "step": 1993
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005838021160189092,
      "loss": 1.9746,
      "step": 1994
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005828456925892159,
      "loss": 1.9193,
      "step": 1995
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005818897309200771,
      "loss": 1.9905,
      "step": 1996
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005809342320696753,
      "loss": 1.971,
      "step": 1997
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005799791970956805,
      "loss": 2.027,
      "step": 1998
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005790246270552498,
      "loss": 1.9842,
      "step": 1999
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005780705230050248,
      "loss": 1.9517,
      "step": 2000
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005771168860011322,
      "loss": 1.9458,
      "step": 2001
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005761637170991809,
      "loss": 1.9974,
      "step": 2002
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005752110173542626,
      "loss": 1.9545,
      "step": 2003
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005742587878209485,
      "loss": 1.8983,
      "step": 2004
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005733070295532898,
      "loss": 1.9746,
      "step": 2005
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005723557436048164,
      "loss": 1.9829,
      "step": 2006
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005714049310285352,
      "loss": 1.9973,
      "step": 2007
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005704545928769288,
      "loss": 1.9644,
      "step": 2008
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005695047302019551,
      "loss": 1.9381,
      "step": 2009
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005685553440550456,
      "loss": 1.9262,
      "step": 2010
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005676064354871035,
      "loss": 1.9782,
      "step": 2011
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005666580055485046,
      "loss": 1.9408,
      "step": 2012
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000565710055289094,
      "loss": 1.9279,
      "step": 2013
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005647625857581863,
      "loss": 2.0392,
      "step": 2014
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005638155980045637,
      "loss": 1.979,
      "step": 2015
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005628690930764757,
      "loss": 1.9294,
      "step": 2016
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000561923072021636,
      "loss": 2.0319,
      "step": 2017
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005609775358872241,
      "loss": 2.027,
      "step": 2018
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000560032485719882,
      "loss": 1.9103,
      "step": 2019
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005590879225657139,
      "loss": 1.9534,
      "step": 2020
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005581438474702851,
      "loss": 1.9715,
      "step": 2021
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005572002614786204,
      "loss": 2.0133,
      "step": 2022
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005562571656352038,
      "loss": 1.9995,
      "step": 2023
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005553145609839754,
      "loss": 1.9175,
      "step": 2024
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005543724485683326,
      "loss": 1.9044,
      "step": 2025
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005534308294311281,
      "loss": 1.9704,
      "step": 2026
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005524897046146681,
      "loss": 1.9641,
      "step": 2027
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005515490751607118,
      "loss": 1.9853,
      "step": 2028
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005506089421104698,
      "loss": 1.9861,
      "step": 2029
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005496693065046035,
      "loss": 2.0724,
      "step": 2030
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005487301693832238,
      "loss": 1.9681,
      "step": 2031
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005477915317858897,
      "loss": 2.0475,
      "step": 2032
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005468533947516068,
      "loss": 1.9518,
      "step": 2033
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005459157593188271,
      "loss": 1.9621,
      "step": 2034
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005449786265254477,
      "loss": 1.988,
      "step": 2035
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005440419974088082,
      "loss": 2.0184,
      "step": 2036
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005431058730056915,
      "loss": 1.9712,
      "step": 2037
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005421702543523218,
      "loss": 1.9376,
      "step": 2038
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005412351424843632,
      "loss": 2.0893,
      "step": 2039
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000540300538436919,
      "loss": 1.979,
      "step": 2040
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005393664432445308,
      "loss": 1.9524,
      "step": 2041
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005384328579411755,
      "loss": 2.0182,
      "step": 2042
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005374997835602669,
      "loss": 1.9625,
      "step": 2043
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005365672211346531,
      "loss": 2.0133,
      "step": 2044
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005356351716966151,
      "loss": 1.9215,
      "step": 2045
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005347036362778663,
      "loss": 2.0577,
      "step": 2046
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005337726159095511,
      "loss": 1.9706,
      "step": 2047
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005328421116222442,
      "loss": 2.0002,
      "step": 2048
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005319121244459475,
      "loss": 2.004,
      "step": 2049
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005309826554100922,
      "loss": 1.9836,
      "step": 2050
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005300537055435352,
      "loss": 1.9888,
      "step": 2051
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005291252758745591,
      "loss": 1.9487,
      "step": 2052
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005281973674308701,
      "loss": 1.8988,
      "step": 2053
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005272699812395983,
      "loss": 2.0093,
      "step": 2054
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005263431183272942,
      "loss": 1.9528,
      "step": 2055
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005254167797199306,
      "loss": 1.9388,
      "step": 2056
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005244909664428993,
      "loss": 1.9626,
      "step": 2057
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005235656795210107,
      "loss": 1.8999,
      "step": 2058
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005226409199784923,
      "loss": 1.9746,
      "step": 2059
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005217166888389883,
      "loss": 2.0194,
      "step": 2060
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005207929871255577,
      "loss": 1.9622,
      "step": 2061
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005198698158606734,
      "loss": 1.9599,
      "step": 2062
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005189471760662212,
      "loss": 1.9329,
      "step": 2063
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005180250687634988,
      "loss": 1.977,
      "step": 2064
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005171034949732141,
      "loss": 1.9651,
      "step": 2065
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005161824557154851,
      "loss": 1.9183,
      "step": 2066
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000515261952009837,
      "loss": 1.9841,
      "step": 2067
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005143419848752028,
      "loss": 2.0135,
      "step": 2068
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000513422555329922,
      "loss": 1.9802,
      "step": 2069
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005125036643917387,
      "loss": 1.9752,
      "step": 2070
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005115853130778003,
      "loss": 1.8947,
      "step": 2071
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005106675024046576,
      "loss": 1.8249,
      "step": 2072
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005097502333882628,
      "loss": 1.8596,
      "step": 2073
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005088335070439678,
      "loss": 1.9211,
      "step": 2074
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005079173243865245,
      "loss": 1.9401,
      "step": 2075
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005070016864300829,
      "loss": 2.0237,
      "step": 2076
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005060865941881902,
      "loss": 2.0019,
      "step": 2077
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000505172048673789,
      "loss": 1.9252,
      "step": 2078
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005042580508992176,
      "loss": 1.9137,
      "step": 2079
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005033446018762066,
      "loss": 1.9629,
      "step": 2080
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005024317026158803,
      "loss": 1.9597,
      "step": 2081
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005015193541287544,
      "loss": 1.9732,
      "step": 2082
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005006075574247343,
      "loss": 1.9463,
      "step": 2083
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004996963135131153,
      "loss": 1.9986,
      "step": 2084
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004987856234025803,
      "loss": 2.0478,
      "step": 2085
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004978754881011999,
      "loss": 2.0484,
      "step": 2086
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004969659086164291,
      "loss": 2.03,
      "step": 2087
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004960568859551091,
      "loss": 1.979,
      "step": 2088
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004951484211234637,
      "loss": 1.9906,
      "step": 2089
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004942405151271007,
      "loss": 1.9414,
      "step": 2090
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004933331689710082,
      "loss": 1.8849,
      "step": 2091
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004924263836595539,
      "loss": 1.9667,
      "step": 2092
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004915201601964861,
      "loss": 1.9723,
      "step": 2093
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004906144995849306,
      "loss": 1.9783,
      "step": 2094
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048970940282739,
      "loss": 2.0199,
      "step": 2095
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000488804870925743,
      "loss": 2.0032,
      "step": 2096
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004879009048812434,
      "loss": 1.9077,
      "step": 2097
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048699750569451727,
      "loss": 1.962,
      "step": 2098
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048609467436556476,
      "loss": 1.9662,
      "step": 2099
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048519241189375664,
      "loss": 1.9683,
      "step": 2100
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004842907192778342,
      "loss": 2.0214,
      "step": 2101
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048338959751590793,
      "loss": 1.9241,
      "step": 2102
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004824890476054563,
      "loss": 1.9346,
      "step": 2103
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048158907054332545,
      "loss": 2.0518,
      "step": 2104
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048068966732572606,
      "loss": 1.9824,
      "step": 2105
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00047979083894823473,
      "loss": 1.9504,
      "step": 2106
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00047889258640579135,
      "loss": 1.9931,
      "step": 2107
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00047799491069269853,
      "loss": 1.9542,
      "step": 2108
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004770978128026203,
      "loss": 1.9004,
      "step": 2109
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004762012937285812,
      "loss": 1.9214,
      "step": 2110
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004753053544629653,
      "loss": 1.9789,
      "step": 2111
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00047440999599751354,
      "loss": 1.9777,
      "step": 2112
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00047351521932332554,
      "loss": 2.0267,
      "step": 2113
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00047262102543085626,
      "loss": 1.9341,
      "step": 2114
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004717274153099156,
      "loss": 2.0125,
      "step": 2115
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00047083438994966723,
      "loss": 1.9983,
      "step": 2116
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000469941950338628,
      "loss": 2.0019,
      "step": 2117
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004690500974646652,
      "loss": 2.0896,
      "step": 2118
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004681588323149978,
      "loss": 1.9337,
      "step": 2119
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004672681558761933,
      "loss": 1.9514,
      "step": 2120
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004663780691341689,
      "loss": 1.9796,
      "step": 2121
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004654885730741882,
      "loss": 2.0195,
      "step": 2122
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00046459966868086014,
      "loss": 1.9899,
      "step": 2123
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004637113569381399,
      "loss": 2.0053,
      "step": 2124
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004628236388293262,
      "loss": 2.0316,
      "step": 2125
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004619365153370608,
      "loss": 1.9939,
      "step": 2126
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00046104998744332724,
      "loss": 2.0152,
      "step": 2127
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00046016405612944955,
      "loss": 2.0263,
      "step": 2128
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000459278722376092,
      "loss": 1.9936,
      "step": 2129
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00045839398716325633,
      "loss": 2.015,
      "step": 2130
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00045750985147028245,
      "loss": 1.9798,
      "step": 2131
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00045662631627584673,
      "loss": 1.9956,
      "step": 2132
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00045574338255796056,
      "loss": 1.9987,
      "step": 2133
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004548610512939697,
      "loss": 1.9597,
      "step": 2134
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00045397932346055324,
      "loss": 1.9754,
      "step": 2135
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004530982000337215,
      "loss": 1.9557,
      "step": 2136
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004522176819888164,
      "loss": 1.9541,
      "step": 2137
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004513377703005099,
      "loss": 1.9493,
      "step": 2138
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004504584659428024,
      "loss": 1.9544,
      "step": 2139
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00044957976988902203,
      "loss": 1.9649,
      "step": 2140
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004487016831118239,
      "loss": 2.0201,
      "step": 2141
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004478242065831887,
      "loss": 1.9699,
      "step": 2142
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004469473412744206,
      "loss": 1.9589,
      "step": 2143
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004460710881561485,
      "loss": 1.9648,
      "step": 2144
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00044519544819832303,
      "loss": 1.9418,
      "step": 2145
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004443204223702163,
      "loss": 1.9355,
      "step": 2146
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004434460116404204,
      "loss": 2.019,
      "step": 2147
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00044257221697684666,
      "loss": 1.9866,
      "step": 2148
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000441699039346725,
      "loss": 1.8919,
      "step": 2149
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004408264797166005,
      "loss": 1.9654,
      "step": 2150
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004399545390523367,
      "loss": 1.9453,
      "step": 2151
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00043908321831911045,
      "loss": 1.9685,
      "step": 2152
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004382125184814124,
      "loss": 2.0329,
      "step": 2153
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004373424405030468,
      "loss": 2.0196,
      "step": 2154
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004364729853471282,
      "loss": 1.9575,
      "step": 2155
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00043560415397608267,
      "loss": 1.9448,
      "step": 2156
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004347359473516457,
      "loss": 1.9914,
      "step": 2157
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00043386836643486115,
      "loss": 1.979,
      "step": 2158
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00043300141218608005,
      "loss": 1.9443,
      "step": 2159
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004321350855649605,
      "loss": 1.9945,
      "step": 2160
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004312693875304645,
      "loss": 1.9386,
      "step": 2161
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00043040431904085944,
      "loss": 2.0018,
      "step": 2162
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00042953988105371533,
      "loss": 1.9771,
      "step": 2163
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004286760745259045,
      "loss": 2.0156,
      "step": 2164
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004278129004136001,
      "loss": 2.0211,
      "step": 2165
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00042695035967227547,
      "loss": 1.9831,
      "step": 2166
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00042608845325670287,
      "loss": 2.0233,
      "step": 2167
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004252271821209516,
      "loss": 1.9886,
      "step": 2168
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00042436654721838873,
      "loss": 1.9618,
      "step": 2169
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004235065495016769,
      "loss": 2.0095,
      "step": 2170
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00042264718992277294,
      "loss": 1.9501,
      "step": 2171
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004217884694329278,
      "loss": 1.967,
      "step": 2172
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004209303889826852,
      "loss": 1.9366,
      "step": 2173
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00042007294952187927,
      "loss": 1.9847,
      "step": 2174
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004192161519996357,
      "loss": 1.9376,
      "step": 2175
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00041835999736436914,
      "loss": 1.9567,
      "step": 2176
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00041750448656378283,
      "loss": 1.9888,
      "step": 2177
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004166496205448671,
      "loss": 1.9446,
      "step": 2178
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004157954002538987,
      "loss": 1.9706,
      "step": 2179
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00041494182663644007,
      "loss": 1.9826,
      "step": 2180
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00041408890063733604,
      "loss": 1.9696,
      "step": 2181
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004132366232007172,
      "loss": 2.0033,
      "step": 2182
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004123849952699942,
      "loss": 2.05,
      "step": 2183
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004115340177878596,
      "loss": 1.9722,
      "step": 2184
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00041068369169628614,
      "loss": 1.9586,
      "step": 2185
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004098340179365244,
      "loss": 1.9695,
      "step": 2186
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000408984997449104,
      "loss": 1.9793,
      "step": 2187
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00040813663117383105,
      "loss": 1.9709,
      "step": 2188
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00040728892004978745,
      "loss": 1.9271,
      "step": 2189
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00040644186501533,
      "loss": 1.9936,
      "step": 2190
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00040559546700808923,
      "loss": 1.9505,
      "step": 2191
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004047497269649687,
      "loss": 1.9424,
      "step": 2192
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00040390464582214247,
      "loss": 1.9882,
      "step": 2193
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004030602245150566,
      "loss": 2.0265,
      "step": 2194
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00040221646397842626,
      "loss": 1.9459,
      "step": 2195
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00040137336514623503,
      "loss": 1.9267,
      "step": 2196
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00040053092895173424,
      "loss": 1.9712,
      "step": 2197
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003996891563274421,
      "loss": 1.8862,
      "step": 2198
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000398848048205141,
      "loss": 1.9396,
      "step": 2199
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000398007605515879,
      "loss": 1.9479,
      "step": 2200
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003971678291899673,
      "loss": 1.9833,
      "step": 2201
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003963287201569793,
      "loss": 1.9612,
      "step": 2202
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003954902793457499,
      "loss": 1.9223,
      "step": 2203
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003946525076843741,
      "loss": 1.9657,
      "step": 2204
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00039381540610020695,
      "loss": 1.9456,
      "step": 2205
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003929789755198603,
      "loss": 1.9493,
      "step": 2206
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003921432168692045,
      "loss": 1.9387,
      "step": 2207
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003913081310733658,
      "loss": 1.9728,
      "step": 2208
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003904737190567256,
      "loss": 2.0324,
      "step": 2209
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003896399817429195,
      "loss": 1.9883,
      "step": 2210
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000388806920054836,
      "loss": 1.955,
      "step": 2211
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003879745349146162,
      "loss": 2.0185,
      "step": 2212
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00038714282724365204,
      "loss": 1.9183,
      "step": 2213
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003863117979625853,
      "loss": 1.9189,
      "step": 2214
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003854814479913075,
      "loss": 1.9507,
      "step": 2215
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003846517782489575,
      "loss": 2.0088,
      "step": 2216
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003838227896539219,
      "loss": 2.0226,
      "step": 2217
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00038299448312383233,
      "loss": 1.9815,
      "step": 2218
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003821668595755663,
      "loss": 1.9582,
      "step": 2219
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000381339919925245,
      "loss": 1.9636,
      "step": 2220
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003805136650882326,
      "loss": 1.9876,
      "step": 2221
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003796880959791353,
      "loss": 2.0374,
      "step": 2222
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00037886321351180053,
      "loss": 1.9742,
      "step": 2223
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00037803901859931457,
      "loss": 1.9888,
      "step": 2224
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00037721551215400375,
      "loss": 1.9456,
      "step": 2225
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000376392695087432,
      "loss": 1.9349,
      "step": 2226
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003755705683103999,
      "loss": 1.9491,
      "step": 2227
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00037474913273294444,
      "loss": 1.9306,
      "step": 2228
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003739283892643368,
      "loss": 1.9115,
      "step": 2229
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00037310833881308304,
      "loss": 1.9544,
      "step": 2230
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00037228898228692066,
      "loss": 1.9816,
      "step": 2231
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00037147032059282024,
      "loss": 1.9918,
      "step": 2232
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003706523546369829,
      "loss": 1.9651,
      "step": 2233
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003698350853248394,
      "loss": 1.9651,
      "step": 2234
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003690185135610499,
      "loss": 2.0082,
      "step": 2235
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003682026402495019,
      "loss": 1.9773,
      "step": 2236
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003673874662933097,
      "loss": 1.874,
      "step": 2237
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003665729925948137,
      "loss": 2.0721,
      "step": 2238
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003657592200555793,
      "loss": 1.8913,
      "step": 2239
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003649461495763956,
      "loss": 2.0257,
      "step": 2240
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036413378205727456,
      "loss": 2.022,
      "step": 2241
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036332211839745,
      "loss": 1.9702,
      "step": 2242
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036251115949537674,
      "loss": 1.9877,
      "step": 2243
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036170090624872934,
      "loss": 2.0161,
      "step": 2244
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036089135955440124,
      "loss": 1.9354,
      "step": 2245
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000360082520308504,
      "loss": 1.8824,
      "step": 2246
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003592743894063658,
      "loss": 1.9692,
      "step": 2247
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003584669677425313,
      "loss": 1.9413,
      "step": 2248
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003576602562107588,
      "loss": 1.9325,
      "step": 2249
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00035685425570402185,
      "loss": 2.0259,
      "step": 2250
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003560489671145064,
      "loss": 1.904,
      "step": 2251
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00035524439133361054,
      "loss": 1.9496,
      "step": 2252
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000354440529251943,
      "loss": 1.9668,
      "step": 2253
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003536373817593234,
      "loss": 1.9451,
      "step": 2254
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003528349497447786,
      "loss": 1.9436,
      "step": 2255
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00035203323409654507,
      "loss": 1.9109,
      "step": 2256
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00035123223570206587,
      "loss": 1.9922,
      "step": 2257
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003504319554479899,
      "loss": 1.9541,
      "step": 2258
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003496323942201712,
      "loss": 2.0256,
      "step": 2259
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00034883355290366827,
      "loss": 1.9635,
      "step": 2260
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00034803543238274236,
      "loss": 1.9784,
      "step": 2261
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003472380335408566,
      "loss": 1.9938,
      "step": 2262
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003464413572606756,
      "loss": 1.9577,
      "step": 2263
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003456454044240642,
      "loss": 1.9367,
      "step": 2264
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00034485017591208645,
      "loss": 1.9984,
      "step": 2265
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00034405567260500437,
      "loss": 1.9536,
      "step": 2266
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003432618953822776,
      "loss": 1.926,
      "step": 2267
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00034246884512256195,
      "loss": 2.014,
      "step": 2268
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00034167652270370786,
      "loss": 1.9619,
      "step": 2269
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000340884929002761,
      "loss": 1.971,
      "step": 2270
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003400940648959602,
      "loss": 1.9645,
      "step": 2271
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003393039312587359,
      "loss": 1.9634,
      "step": 2272
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003385145289657118,
      "loss": 1.983,
      "step": 2273
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00033772585889069986,
      "loss": 2.0076,
      "step": 2274
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00033693792190670293,
      "loss": 1.9193,
      "step": 2275
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00033615071888591175,
      "loss": 1.9535,
      "step": 2276
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00033536425069970513,
      "loss": 1.9234,
      "step": 2277
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003345785182186478,
      "loss": 1.9578,
      "step": 2278
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00033379352231249125,
      "loss": 1.9482,
      "step": 2279
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00033300926385016995,
      "loss": 1.9942,
      "step": 2280
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003322257436998034,
      "loss": 1.9828,
      "step": 2281
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003314429627286936,
      "loss": 1.8799,
      "step": 2282
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00033066092180332387,
      "loss": 1.989,
      "step": 2283
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003298796217893588,
      "loss": 1.9485,
      "step": 2284
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00032909906355164275,
      "loss": 1.9741,
      "step": 2285
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003283192479541992,
      "loss": 1.9581,
      "step": 2286
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00032754017586022864,
      "loss": 1.9329,
      "step": 2287
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00032676184813210964,
      "loss": 1.9574,
      "step": 2288
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00032598426563139625,
      "loss": 1.9696,
      "step": 2289
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00032520742921881787,
      "loss": 1.88,
      "step": 2290
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00032443133975427785,
      "loss": 1.9967,
      "step": 2291
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003236559980968532,
      "loss": 1.9805,
      "step": 2292
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003228814051047919,
      "loss": 1.9903,
      "step": 2293
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003221075616355147,
      "loss": 1.9859,
      "step": 2294
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00032133446854561165,
      "loss": 1.9283,
      "step": 2295
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00032056212669084286,
      "loss": 2.0057,
      "step": 2296
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00031979053692613645,
      "loss": 1.897,
      "step": 2297
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003190197001055882,
      "loss": 1.9636,
      "step": 2298
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003182496170824608,
      "loss": 1.9436,
      "step": 2299
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003174802887091813,
      "loss": 2.0081,
      "step": 2300
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003167117158373427,
      "loss": 2.0254,
      "step": 2301
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00031594389931770115,
      "loss": 1.9506,
      "step": 2302
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00031517684000017545,
      "loss": 1.9189,
      "step": 2303
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003144105387338474,
      "loss": 1.9885,
      "step": 2304
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00031364499636695777,
      "loss": 1.9837,
      "step": 2305
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00031288021374690865,
      "loss": 2.0128,
      "step": 2306
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00031211619172026063,
      "loss": 1.9322,
      "step": 2307
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003113529311327324,
      "loss": 2.0118,
      "step": 2308
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003105904328292002,
      "loss": 1.9332,
      "step": 2309
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00030982869765369594,
      "loss": 1.9741,
      "step": 2310
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003090677264494074,
      "loss": 1.9624,
      "step": 2311
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00030830752005867555,
      "loss": 1.9682,
      "step": 2312
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00030754807932299613,
      "loss": 2.0543,
      "step": 2313
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003067894050830166,
      "loss": 1.9313,
      "step": 2314
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00030603149817853603,
      "loss": 1.9484,
      "step": 2315
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00030527435944850445,
      "loss": 1.9766,
      "step": 2316
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003045179897310213,
      "loss": 2.0646,
      "step": 2317
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003037623898633345,
      "loss": 1.9794,
      "step": 2318
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003030075606818402,
      "loss": 1.9555,
      "step": 2319
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00030225350302208134,
      "loss": 2.0476,
      "step": 2320
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000301500217718747,
      "loss": 2.0197,
      "step": 2321
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003007477056056711,
      "loss": 1.9362,
      "step": 2322
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00029999596751583167,
      "loss": 1.9652,
      "step": 2323
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00029924500428135046,
      "loss": 2.022,
      "step": 2324
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002984948167334904,
      "loss": 1.9751,
      "step": 2325
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00029774540570265694,
      "loss": 2.0562,
      "step": 2326
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002969967720183954,
      "loss": 1.9915,
      "step": 2327
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00029624891650939067,
      "loss": 1.9913,
      "step": 2328
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00029550184000346646,
      "loss": 1.9735,
      "step": 2329
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00029475554332758437,
      "loss": 1.9508,
      "step": 2330
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002940100273078418,
      "loss": 1.9459,
      "step": 2331
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002932652927694729,
      "loss": 1.9865,
      "step": 2332
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002925213405368463,
      "loss": 1.95,
      "step": 2333
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00029177817143346575,
      "loss": 1.9544,
      "step": 2334
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002910357862819668,
      "loss": 1.9385,
      "step": 2335
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00029029418590411813,
      "loss": 2.0197,
      "step": 2336
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002895533711208187,
      "loss": 2.0131,
      "step": 2337
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002888133427520987,
      "loss": 1.9476,
      "step": 2338
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002880741016171178,
      "loss": 1.933,
      "step": 2339
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002873356485341639,
      "loss": 1.8911,
      "step": 2340
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00028659798432065296,
      "loss": 1.935,
      "step": 2341
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00028586110979312776,
      "loss": 1.8985,
      "step": 2342
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00028512502576725585,
      "loss": 1.9375,
      "step": 2343
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00028438973305783136,
      "loss": 1.9293,
      "step": 2344
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002836552324787713,
      "loss": 1.9747,
      "step": 2345
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002829215248431166,
      "loss": 2.0264,
      "step": 2346
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00028218861096302995,
      "loss": 1.9441,
      "step": 2347
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002814564916497957,
      "loss": 1.9944,
      "step": 2348
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00028072516771381897,
      "loss": 2.0109,
      "step": 2349
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00027999463996462317,
      "loss": 1.9221,
      "step": 2350
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002792649092108518,
      "loss": 1.9733,
      "step": 2351
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002785359762602655,
      "loss": 1.9998,
      "step": 2352
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00027780784191974196,
      "loss": 1.9558,
      "step": 2353
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002770805069952749,
      "loss": 1.9665,
      "step": 2354
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00027635397229197324,
      "loss": 1.9463,
      "step": 2355
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00027562823861405927,
      "loss": 1.9321,
      "step": 2356
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00027490330676486975,
      "loss": 1.9446,
      "step": 2357
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002741791775468532,
      "loss": 1.9433,
      "step": 2358
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00027345585176156994,
      "loss": 2.0034,
      "step": 2359
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002727333302096909,
      "loss": 1.9508,
      "step": 2360
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002720116136909968,
      "loss": 1.9914,
      "step": 2361
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002712907030043774,
      "loss": 1.9442,
      "step": 2362
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002705705989478293,
      "loss": 2.0221,
      "step": 2363
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00026985130231845823,
      "loss": 1.92,
      "step": 2364
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002691328139124747,
      "loss": 2.0059,
      "step": 2365
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00026841513452519506,
      "loss": 1.9739,
      "step": 2366
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002676982649510402,
      "loss": 1.9855,
      "step": 2367
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002669822059835341,
      "loss": 1.9393,
      "step": 2368
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002662669584153038,
      "loss": 1.961,
      "step": 2369
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002655525230380783,
      "loss": 1.8938,
      "step": 2370
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002648389006426876,
      "loss": 1.9559,
      "step": 2371
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00026412609201906137,
      "loss": 1.9746,
      "step": 2372
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00026341409795622897,
      "loss": 2.0059,
      "step": 2373
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00026270291924231803,
      "loss": 1.9679,
      "step": 2374
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000261992556664553,
      "loss": 1.9359,
      "step": 2375
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002612830110092557,
      "loss": 1.9798,
      "step": 2376
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002605742830618433,
      "loss": 1.9714,
      "step": 2377
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00025986637360682796,
      "loss": 1.8982,
      "step": 2378
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002591592834278159,
      "loss": 2.0296,
      "step": 2379
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002584530133075066,
      "loss": 2.0043,
      "step": 2380
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00025774756402769083,
      "loss": 1.9727,
      "step": 2381
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002570429363692518,
      "loss": 1.8878,
      "step": 2382
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000256339131112163,
      "loss": 2.0252,
      "step": 2383
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00025563614903548735,
      "loss": 1.9763,
      "step": 2384
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002549339909173768,
      "loss": 1.9351,
      "step": 2385
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00025423265753507095,
      "loss": 1.9967,
      "step": 2386
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002535321496648972,
      "loss": 1.9446,
      "step": 2387
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002528324680822679,
      "loss": 1.9801,
      "step": 2388
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00025213361356168175,
      "loss": 2.0671,
      "step": 2389
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00025143558687672164,
      "loss": 1.9332,
      "step": 2390
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002507383888000543,
      "loss": 1.9618,
      "step": 2391
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002500420201034289,
      "loss": 2.0158,
      "step": 2392
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00024934648155767726,
      "loss": 1.9798,
      "step": 2393
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00024865177393271063,
      "loss": 1.9496,
      "step": 2394
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002479578979975227,
      "loss": 1.9786,
      "step": 2395
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002472648545201851,
      "loss": 1.9872,
      "step": 2396
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002465726442678482,
      "loss": 1.939,
      "step": 2397
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002458812680067407,
      "loss": 1.9868,
      "step": 2398
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002451907265021669,
      "loss": 1.9149,
      "step": 2399
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002445010205185081,
      "loss": 1.9196,
      "step": 2400
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002438121508192205,
      "loss": 1.9319,
      "step": 2401
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00024312411816683455,
      "loss": 1.9896,
      "step": 2402
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00024243692332295396,
      "loss": 1.9429,
      "step": 2403
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00024175056704825549,
      "loss": 1.945,
      "step": 2404
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00024106505010248737,
      "loss": 1.9208,
      "step": 2405
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00024038037324446848,
      "loss": 1.973,
      "step": 2406
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00023969653723208818,
      "loss": 1.9296,
      "step": 2407
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00023901354282230492,
      "loss": 1.8546,
      "step": 2408
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00023833139077114574,
      "loss": 1.9356,
      "step": 2409
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00023765008183370507,
      "loss": 1.974,
      "step": 2410
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002369696167641442,
      "loss": 1.9648,
      "step": 2411
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00023628999631569026,
      "loss": 1.9527,
      "step": 2412
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00023561122124063504,
      "loss": 1.9482,
      "step": 2413
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002349332922903351,
      "loss": 1.9346,
      "step": 2414
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00023425621021521038,
      "loss": 1.9868,
      "step": 2415
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002335799757647431,
      "loss": 2.0049,
      "step": 2416
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002329045896874774,
      "loss": 1.9323,
      "step": 2417
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002322300527310186,
      "loss": 1.9298,
      "step": 2418
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002315563656420312,
      "loss": 1.9352,
      "step": 2419
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00023088352916623988,
      "loss": 1.9547,
      "step": 2420
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00023021154404842737,
      "loss": 1.9246,
      "step": 2421
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022954041103243395,
      "loss": 1.9129,
      "step": 2422
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022887013086115706,
      "loss": 2.0028,
      "step": 2423
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022820070427654959,
      "loss": 1.9481,
      "step": 2424
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022753213201961986,
      "loss": 1.8996,
      "step": 2425
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022686441483043052,
      "loss": 1.913,
      "step": 2426
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022619755344809755,
      "loss": 2.0204,
      "step": 2427
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022553154861078983,
      "loss": 1.9541,
      "step": 2428
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.000224866401055728,
      "loss": 1.9751,
      "step": 2429
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002242021115191839,
      "loss": 1.9468,
      "step": 2430
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022353868073647897,
      "loss": 2.0636,
      "step": 2431
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022287610944198488,
      "loss": 1.9422,
      "step": 2432
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002222143983691215,
      "loss": 2.0488,
      "step": 2433
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022155354825035656,
      "loss": 1.8892,
      "step": 2434
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022089355981720472,
      "loss": 1.953,
      "step": 2435
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022023443380022735,
      "loss": 1.8845,
      "step": 2436
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00021957617092903004,
      "loss": 1.9564,
      "step": 2437
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00021891877193226384,
      "loss": 1.9575,
      "step": 2438
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002182622375376233,
      "loss": 1.991,
      "step": 2439
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002176065684718461,
      "loss": 1.974,
      "step": 2440
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00021695176546071183,
      "loss": 1.9516,
      "step": 2441
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002162978292290414,
      "loss": 1.9349,
      "step": 2442
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002156447605006967,
      "loss": 1.9743,
      "step": 2443
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00021499255999857846,
      "loss": 1.9504,
      "step": 2444
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00021434122844462723,
      "loss": 1.94,
      "step": 2445
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00021369076655982112,
      "loss": 2.0271,
      "step": 2446
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00021304117506417596,
      "loss": 1.9661,
      "step": 2447
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00021239245467674395,
      "loss": 1.9354,
      "step": 2448
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002117446061156133,
      "loss": 1.9588,
      "step": 2449
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002110976300979065,
      "loss": 1.9377,
      "step": 2450
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00021045152733978068,
      "loss": 1.9711,
      "step": 2451
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002098062985564263,
      "loss": 2.0114,
      "step": 2452
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002091619444620666,
      "loss": 1.925,
      "step": 2453
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00020851846576995604,
      "loss": 1.99,
      "step": 2454
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002078758631923806,
      "loss": 2.0181,
      "step": 2455
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00020723413744065623,
      "loss": 2.0098,
      "step": 2456
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002065932892251282,
      "loss": 1.9453,
      "step": 2457
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00020595331925517068,
      "loss": 2.0416,
      "step": 2458
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00020531422823918545,
      "loss": 1.9654,
      "step": 2459
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00020467601688460148,
      "loss": 1.9308,
      "step": 2460
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00020403868589787412,
      "loss": 2.0584,
      "step": 2461
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002034022359844837,
      "loss": 2.0132,
      "step": 2462
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00020276666784893572,
      "loss": 1.9088,
      "step": 2463
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00020213198219475959,
      "loss": 1.9319,
      "step": 2464
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00020149817972450791,
      "loss": 1.9288,
      "step": 2465
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00020086526113975546,
      "loss": 2.0215,
      "step": 2466
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002002332271410986,
      "loss": 1.9604,
      "step": 2467
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019960207842815514,
      "loss": 1.9136,
      "step": 2468
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019897181569956168,
      "loss": 1.9763,
      "step": 2469
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019834243965297527,
      "loss": 2.0198,
      "step": 2470
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019771395098507082,
      "loss": 1.929,
      "step": 2471
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019708635039154154,
      "loss": 1.9819,
      "step": 2472
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019645963856709692,
      "loss": 2.0372,
      "step": 2473
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019583381620546348,
      "loss": 1.9635,
      "step": 2474
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019520888399938207,
      "loss": 1.9447,
      "step": 2475
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019458484264060904,
      "loss": 1.9752,
      "step": 2476
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019396169281991438,
      "loss": 1.9081,
      "step": 2477
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019333943522708132,
      "loss": 2.0289,
      "step": 2478
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001927180705509053,
      "loss": 1.9835,
      "step": 2479
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019209759947919335,
      "loss": 1.9456,
      "step": 2480
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001914780226987638,
      "loss": 1.9096,
      "step": 2481
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001908593408954441,
      "loss": 1.9806,
      "step": 2482
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000190241554754072,
      "loss": 2.0027,
      "step": 2483
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001896246649584932,
      "loss": 1.954,
      "step": 2484
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018900867219156126,
      "loss": 1.9592,
      "step": 2485
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018839357713513783,
      "loss": 2.0379,
      "step": 2486
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018777938047008914,
      "loss": 1.9395,
      "step": 2487
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000187166082876288,
      "loss": 1.8718,
      "step": 2488
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018655368503261194,
      "loss": 1.9868,
      "step": 2489
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018594218761694238,
      "loss": 2.0125,
      "step": 2490
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018533159130616395,
      "loss": 1.9741,
      "step": 2491
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018472189677616415,
      "loss": 1.9644,
      "step": 2492
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018411310470183207,
      "loss": 1.9811,
      "step": 2493
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018350521575705747,
      "loss": 1.938,
      "step": 2494
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018289823061473098,
      "loss": 1.9413,
      "step": 2495
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001822921499467427,
      "loss": 1.9771,
      "step": 2496
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001816869744239812,
      "loss": 1.9173,
      "step": 2497
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018108270471633336,
      "loss": 1.9519,
      "step": 2498
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018047934149268376,
      "loss": 2.0085,
      "step": 2499
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017987688542091252,
      "loss": 1.9597,
      "step": 2500
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017927533716789645,
      "loss": 1.9292,
      "step": 2501
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017867469739950748,
      "loss": 1.9077,
      "step": 2502
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017807496678061164,
      "loss": 2.0079,
      "step": 2503
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017747614597506844,
      "loss": 1.8984,
      "step": 2504
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001768782356457308,
      "loss": 2.0036,
      "step": 2505
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017628123645444348,
      "loss": 1.9819,
      "step": 2506
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017568514906204246,
      "loss": 1.957,
      "step": 2507
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017508997412835482,
      "loss": 1.9369,
      "step": 2508
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001744957123121973,
      "loss": 1.9608,
      "step": 2509
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00017390236427137628,
      "loss": 1.9574,
      "step": 2510
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001733099306626863,
      "loss": 1.9941,
      "step": 2511
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00017271841214191007,
      "loss": 1.9517,
      "step": 2512
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00017212780936381666,
      "loss": 1.9929,
      "step": 2513
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001715381229821621,
      "loss": 2.0394,
      "step": 2514
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001709493536496878,
      "loss": 1.9705,
      "step": 2515
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00017036150201811984,
      "loss": 1.9897,
      "step": 2516
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016977456873816966,
      "loss": 1.9434,
      "step": 2517
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016918855445953042,
      "loss": 1.9678,
      "step": 2518
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016860345983087888,
      "loss": 1.93,
      "step": 2519
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000168019285499874,
      "loss": 1.9051,
      "step": 2520
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016743603211315561,
      "loss": 1.9492,
      "step": 2521
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001668537003163444,
      "loss": 1.988,
      "step": 2522
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016627229075404082,
      "loss": 1.9203,
      "step": 2523
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016569180406982465,
      "loss": 2.0124,
      "step": 2524
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001651122409062533,
      "loss": 1.9533,
      "step": 2525
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001645336019048631,
      "loss": 1.9816,
      "step": 2526
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016395588770616666,
      "loss": 1.9175,
      "step": 2527
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016337909894965309,
      "loss": 1.892,
      "step": 2528
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016280323627378701,
      "loss": 1.8977,
      "step": 2529
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001622283003160081,
      "loss": 1.9744,
      "step": 2530
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001616542917127304,
      "loss": 1.9323,
      "step": 2531
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001610812110993405,
      "loss": 1.9163,
      "step": 2532
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016050905911019886,
      "loss": 1.9435,
      "step": 2533
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00015993783637863757,
      "loss": 1.9758,
      "step": 2534
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00015936754353696004,
      "loss": 2.0101,
      "step": 2535
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00015879818121644051,
      "loss": 2.0003,
      "step": 2536
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00015822975004732331,
      "loss": 1.9678,
      "step": 2537
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00015766225065882145,
      "loss": 1.9131,
      "step": 2538
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001570956836791172,
      "loss": 1.9847,
      "step": 2539
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00015653004973536033,
      "loss": 2.0067,
      "step": 2540
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015596534945366814,
      "loss": 1.9516,
      "step": 2541
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015540158345912403,
      "loss": 1.9593,
      "step": 2542
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015483875237577748,
      "loss": 1.9871,
      "step": 2543
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015427685682664329,
      "loss": 1.9421,
      "step": 2544
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015371589743369996,
      "loss": 1.995,
      "step": 2545
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015315587481789006,
      "loss": 1.9499,
      "step": 2546
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015259678959911993,
      "loss": 1.9086,
      "step": 2547
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015203864239625732,
      "loss": 1.9316,
      "step": 2548
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015148143382713242,
      "loss": 2.0392,
      "step": 2549
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015092516450853556,
      "loss": 1.9784,
      "step": 2550
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015036983505621794,
      "loss": 1.9129,
      "step": 2551
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014981544608489038,
      "loss": 1.9916,
      "step": 2552
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014926199820822274,
      "loss": 2.0029,
      "step": 2553
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014870949203884266,
      "loss": 1.995,
      "step": 2554
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014815792818833617,
      "loss": 1.9598,
      "step": 2555
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014760730726724524,
      "loss": 2.0044,
      "step": 2556
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014705762988506888,
      "loss": 2.0195,
      "step": 2557
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014650889665026134,
      "loss": 1.9166,
      "step": 2558
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001459611081702319,
      "loss": 1.9468,
      "step": 2559
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014541426505134382,
      "loss": 1.9916,
      "step": 2560
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014486836789891422,
      "loss": 1.9183,
      "step": 2561
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014432341731721311,
      "loss": 2.0009,
      "step": 2562
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014377941390946215,
      "loss": 1.94,
      "step": 2563
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001432363582778351,
      "loss": 1.9126,
      "step": 2564
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014269425102345646,
      "loss": 1.97,
      "step": 2565
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014215309274640098,
      "loss": 1.9434,
      "step": 2566
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014161288404569296,
      "loss": 1.8925,
      "step": 2567
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014107362551930535,
      "loss": 1.9809,
      "step": 2568
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014053531776415996,
      "loss": 1.942,
      "step": 2569
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00013999796137612508,
      "loss": 2.0158,
      "step": 2570
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013946155695001683,
      "loss": 1.9768,
      "step": 2571
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013892610507959725,
      "loss": 1.9459,
      "step": 2572
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001383916063575741,
      "loss": 1.9826,
      "step": 2573
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013785806137559987,
      "loss": 1.9974,
      "step": 2574
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001373254707242717,
      "loss": 1.9418,
      "step": 2575
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001367938349931296,
      "loss": 2.0014,
      "step": 2576
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013626315477065709,
      "loss": 1.9758,
      "step": 2577
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013573343064428035,
      "loss": 1.9215,
      "step": 2578
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013520466320036652,
      "loss": 1.9666,
      "step": 2579
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013467685302422439,
      "loss": 1.9703,
      "step": 2580
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001341500007001023,
      "loss": 1.9413,
      "step": 2581
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001336241068111892,
      "loss": 1.9649,
      "step": 2582
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013309917193961253,
      "loss": 1.97,
      "step": 2583
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013257519666643835,
      "loss": 2.0128,
      "step": 2584
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013205218157167077,
      "loss": 1.8954,
      "step": 2585
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013153012723425052,
      "loss": 1.9999,
      "step": 2586
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013100903423205558,
      "loss": 1.9044,
      "step": 2587
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013048890314189875,
      "loss": 1.9527,
      "step": 2588
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001299697345395291,
      "loss": 1.9298,
      "step": 2589
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012945152899962952,
      "loss": 1.9749,
      "step": 2590
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012893428709581745,
      "loss": 2.0421,
      "step": 2591
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001284180094006433,
      "loss": 1.9592,
      "step": 2592
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001279026964855905,
      "loss": 1.9187,
      "step": 2593
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012738834892107387,
      "loss": 1.9967,
      "step": 2594
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012687496727644022,
      "loss": 1.921,
      "step": 2595
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012636255211996716,
      "loss": 2.0146,
      "step": 2596
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012585110401886214,
      "loss": 1.9966,
      "step": 2597
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012534062353926245,
      "loss": 1.9378,
      "step": 2598
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012483111124623425,
      "loss": 1.9276,
      "step": 2599
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012432256770377194,
      "loss": 1.971,
      "step": 2600
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001238149934747972,
      "loss": 1.9307,
      "step": 2601
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012330838912115926,
      "loss": 1.9472,
      "step": 2602
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001228027552036337,
      "loss": 1.9212,
      "step": 2603
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012229809228192178,
      "loss": 1.9391,
      "step": 2604
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012179440091464989,
      "loss": 1.9403,
      "step": 2605
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000121291681659369,
      "loss": 2.0057,
      "step": 2606
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001207899350725542,
      "loss": 1.9326,
      "step": 2607
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012028916170960358,
      "loss": 1.9497,
      "step": 2608
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011978936212483838,
      "loss": 2.0538,
      "step": 2609
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011929053687150138,
      "loss": 1.9669,
      "step": 2610
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011879268650175735,
      "loss": 1.9206,
      "step": 2611
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011829581156669189,
      "loss": 1.8806,
      "step": 2612
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001177999126163103,
      "loss": 1.9562,
      "step": 2613
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011730499019953799,
      "loss": 2.0012,
      "step": 2614
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011681104486421956,
      "loss": 1.9862,
      "step": 2615
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011631807715711772,
      "loss": 1.9657,
      "step": 2616
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011582608762391322,
      "loss": 1.9119,
      "step": 2617
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011533507680920408,
      "loss": 1.8177,
      "step": 2618
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011484504525650441,
      "loss": 1.9775,
      "step": 2619
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011435599350824499,
      "loss": 1.9729,
      "step": 2620
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001138679221057719,
      "loss": 1.9679,
      "step": 2621
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011338083158934586,
      "loss": 1.9864,
      "step": 2622
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011289472249814193,
      "loss": 1.9068,
      "step": 2623
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011240959537024864,
      "loss": 1.9753,
      "step": 2624
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011192545074266803,
      "loss": 2.0497,
      "step": 2625
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011144228915131382,
      "loss": 1.86,
      "step": 2626
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00011096011113101224,
      "loss": 2.0205,
      "step": 2627
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001104789172155004,
      "loss": 1.9394,
      "step": 2628
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00010999870793742628,
      "loss": 1.9734,
      "step": 2629
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00010951948382834797,
      "loss": 2.0051,
      "step": 2630
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00010904124541873295,
      "loss": 1.982,
      "step": 2631
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00010856399323795729,
      "loss": 1.9807,
      "step": 2632
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010808772781430586,
      "loss": 1.962,
      "step": 2633
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010761244967497109,
      "loss": 1.933,
      "step": 2634
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010713815934605254,
      "loss": 2.0031,
      "step": 2635
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010666485735255627,
      "loss": 1.9763,
      "step": 2636
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010619254421839442,
      "loss": 1.9772,
      "step": 2637
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010572122046638456,
      "loss": 1.9692,
      "step": 2638
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010525088661824888,
      "loss": 1.9354,
      "step": 2639
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010478154319461419,
      "loss": 2.0075,
      "step": 2640
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010431319071501044,
      "loss": 1.9242,
      "step": 2641
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010384582969787126,
      "loss": 1.9957,
      "step": 2642
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010337946066053238,
      "loss": 1.9888,
      "step": 2643
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010291408411923153,
      "loss": 2.0269,
      "step": 2644
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010244970058910796,
      "loss": 1.9963,
      "step": 2645
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010198631058420161,
      "loss": 1.9741,
      "step": 2646
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001015239146174528,
      "loss": 1.9234,
      "step": 2647
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010106251320070137,
      "loss": 1.8878,
      "step": 2648
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001006021068446863,
      "loss": 2.0332,
      "step": 2649
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00010014269605904546,
      "loss": 1.9637,
      "step": 2650
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.968428135231378e-05,
      "loss": 1.9624,
      "step": 2651
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.922686323192454e-05,
      "loss": 2.0193,
      "step": 2652
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.877044220420739e-05,
      "loss": 1.9107,
      "step": 2653
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.831501877438843e-05,
      "loss": 1.9675,
      "step": 2654
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.786059344658948e-05,
      "loss": 1.9073,
      "step": 2655
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.740716672382765e-05,
      "loss": 1.9017,
      "step": 2656
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.695473910801411e-05,
      "loss": 1.9545,
      "step": 2657
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.65033110999548e-05,
      "loss": 2.0305,
      "step": 2658
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.605288319934868e-05,
      "loss": 2.0049,
      "step": 2659
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.560345590478803e-05,
      "loss": 1.9788,
      "step": 2660
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.515502971375722e-05,
      "loss": 2.0044,
      "step": 2661
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.470760512263254e-05,
      "loss": 1.9245,
      "step": 2662
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.426118262668204e-05,
      "loss": 2.0141,
      "step": 2663
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.381576272006343e-05,
      "loss": 1.8707,
      "step": 2664
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.337134589582564e-05,
      "loss": 2.0109,
      "step": 2665
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.292793264590693e-05,
      "loss": 1.9906,
      "step": 2666
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.24855234611347e-05,
      "loss": 1.9607,
      "step": 2667
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.204411883122477e-05,
      "loss": 2.0099,
      "step": 2668
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.160371924478118e-05,
      "loss": 1.9039,
      "step": 2669
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.116432518929529e-05,
      "loss": 1.9966,
      "step": 2670
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.072593715114564e-05,
      "loss": 1.9326,
      "step": 2671
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.028855561559691e-05,
      "loss": 1.9561,
      "step": 2672
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.985218106679983e-05,
      "loss": 1.9271,
      "step": 2673
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.941681398779055e-05,
      "loss": 1.9791,
      "step": 2674
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.898245486048962e-05,
      "loss": 1.9487,
      "step": 2675
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.854910416570217e-05,
      "loss": 1.9229,
      "step": 2676
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.811676238311705e-05,
      "loss": 1.9026,
      "step": 2677
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.768542999130646e-05,
      "loss": 1.9977,
      "step": 2678
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.725510746772491e-05,
      "loss": 2.0328,
      "step": 2679
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.682579528870926e-05,
      "loss": 1.9329,
      "step": 2680
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.639749392947815e-05,
      "loss": 1.9179,
      "step": 2681
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.59702038641309e-05,
      "loss": 1.9613,
      "step": 2682
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.554392556564772e-05,
      "loss": 1.9194,
      "step": 2683
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.511865950588882e-05,
      "loss": 1.9542,
      "step": 2684
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.469440615559387e-05,
      "loss": 1.9502,
      "step": 2685
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.427116598438156e-05,
      "loss": 1.9604,
      "step": 2686
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.384893946074901e-05,
      "loss": 1.9564,
      "step": 2687
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.342772705207169e-05,
      "loss": 2.019,
      "step": 2688
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.300752922460175e-05,
      "loss": 1.9495,
      "step": 2689
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.258834644346891e-05,
      "loss": 2.0014,
      "step": 2690
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.21701791726791e-05,
      "loss": 1.9631,
      "step": 2691
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.175302787511407e-05,
      "loss": 1.9068,
      "step": 2692
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.13368930125311e-05,
      "loss": 1.9955,
      "step": 2693
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.092177504556253e-05,
      "loss": 1.9375,
      "step": 2694
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.050767443371442e-05,
      "loss": 2.0251,
      "step": 2695
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.009459163536725e-05,
      "loss": 1.8723,
      "step": 2696
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.968252710777479e-05,
      "loss": 1.9554,
      "step": 2697
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.927148130706341e-05,
      "loss": 1.9461,
      "step": 2698
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.886145468823214e-05,
      "loss": 1.9604,
      "step": 2699
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.845244770515158e-05,
      "loss": 1.9491,
      "step": 2700
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.804446081056371e-05,
      "loss": 1.9623,
      "step": 2701
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.763749445608159e-05,
      "loss": 1.8987,
      "step": 2702
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.723154909218832e-05,
      "loss": 2.0214,
      "step": 2703
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.682662516823691e-05,
      "loss": 1.9959,
      "step": 2704
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.64227231324498e-05,
      "loss": 1.9553,
      "step": 2705
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.601984343191837e-05,
      "loss": 1.9982,
      "step": 2706
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.561798651260177e-05,
      "loss": 1.972,
      "step": 2707
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.521715281932773e-05,
      "loss": 1.988,
      "step": 2708
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.481734279579088e-05,
      "loss": 1.8983,
      "step": 2709
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.441855688455302e-05,
      "loss": 1.9617,
      "step": 2710
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.4020795527042e-05,
      "loss": 1.9713,
      "step": 2711
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.362405916355208e-05,
      "loss": 1.9556,
      "step": 2712
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.32283482332421e-05,
      "loss": 1.9672,
      "step": 2713
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.283366317413654e-05,
      "loss": 1.9956,
      "step": 2714
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.244000442312404e-05,
      "loss": 1.9825,
      "step": 2715
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.204737241595738e-05,
      "loss": 1.9452,
      "step": 2716
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.165576758725246e-05,
      "loss": 2.0359,
      "step": 2717
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.126519037048828e-05,
      "loss": 2.0188,
      "step": 2718
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.087564119800694e-05,
      "loss": 2.0544,
      "step": 2719
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.048712050101135e-05,
      "loss": 1.9853,
      "step": 2720
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.009962870956699e-05,
      "loss": 1.9886,
      "step": 2721
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.971316625260016e-05,
      "loss": 2.0083,
      "step": 2722
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.932773355789746e-05,
      "loss": 1.9832,
      "step": 2723
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.894333105210615e-05,
      "loss": 1.954,
      "step": 2724
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.855995916073255e-05,
      "loss": 1.9741,
      "step": 2725
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.817761830814284e-05,
      "loss": 1.863,
      "step": 2726
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.779630891756106e-05,
      "loss": 2.007,
      "step": 2727
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.741603141107011e-05,
      "loss": 1.9566,
      "step": 2728
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.70367862096104e-05,
      "loss": 1.9721,
      "step": 2729
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.665857373298012e-05,
      "loss": 1.9892,
      "step": 2730
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.628139439983394e-05,
      "loss": 2.0165,
      "step": 2731
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.590524862768254e-05,
      "loss": 1.9325,
      "step": 2732
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.553013683289311e-05,
      "loss": 1.9109,
      "step": 2733
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.515605943068803e-05,
      "loss": 2.0098,
      "step": 2734
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.478301683514487e-05,
      "loss": 1.9236,
      "step": 2735
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.441100945919542e-05,
      "loss": 2.003,
      "step": 2736
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.404003771462618e-05,
      "loss": 1.9595,
      "step": 2737
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.367010201207624e-05,
      "loss": 1.9531,
      "step": 2738
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.330120276103879e-05,
      "loss": 1.9962,
      "step": 2739
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.293334036985943e-05,
      "loss": 1.9816,
      "step": 2740
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.256651524573598e-05,
      "loss": 2.0402,
      "step": 2741
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.220072779471808e-05,
      "loss": 2.0014,
      "step": 2742
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.183597842170685e-05,
      "loss": 1.9177,
      "step": 2743
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.147226753045442e-05,
      "loss": 2.0132,
      "step": 2744
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.110959552356288e-05,
      "loss": 1.9822,
      "step": 2745
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.0747962802484846e-05,
      "loss": 1.9436,
      "step": 2746
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.038736976752235e-05,
      "loss": 1.9709,
      "step": 2747
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.0027816817826653e-05,
      "loss": 2.0005,
      "step": 2748
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.9669304351397614e-05,
      "loss": 2.0105,
      "step": 2749
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.9311832765083564e-05,
      "loss": 1.9153,
      "step": 2750
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.8955402454580086e-05,
      "loss": 1.9567,
      "step": 2751
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.860001381443081e-05,
      "loss": 1.92,
      "step": 2752
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.8245667238025935e-05,
      "loss": 1.9766,
      "step": 2753
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.7892363117602265e-05,
      "loss": 1.9901,
      "step": 2754
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.754010184424263e-05,
      "loss": 1.9029,
      "step": 2755
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.718888380787579e-05,
      "loss": 2.0237,
      "step": 2756
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.683870939727531e-05,
      "loss": 1.8976,
      "step": 2757
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.6489579000059575e-05,
      "loss": 1.9614,
      "step": 2758
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.614149300269156e-05,
      "loss": 1.9701,
      "step": 2759
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.579445179047793e-05,
      "loss": 1.9479,
      "step": 2760
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.544845574756918e-05,
      "loss": 1.9062,
      "step": 2761
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.510350525695862e-05,
      "loss": 1.9703,
      "step": 2762
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.4759600700482136e-05,
      "loss": 1.987,
      "step": 2763
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.441674245881789e-05,
      "loss": 1.9827,
      "step": 2764
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.407493091148608e-05,
      "loss": 1.9745,
      "step": 2765
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.373416643684803e-05,
      "loss": 1.8856,
      "step": 2766
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.339444941210614e-05,
      "loss": 1.9656,
      "step": 2767
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.305578021330315e-05,
      "loss": 1.9058,
      "step": 2768
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.2718159215322525e-05,
      "loss": 1.9433,
      "step": 2769
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.238158679188654e-05,
      "loss": 1.9865,
      "step": 2770
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.20460633155575e-05,
      "loss": 1.9979,
      "step": 2771
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.1711589157736215e-05,
      "loss": 2.0405,
      "step": 2772
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.13781646886623e-05,
      "loss": 1.9185,
      "step": 2773
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.104579027741318e-05,
      "loss": 1.9911,
      "step": 2774
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.0714466291904126e-05,
      "loss": 2.0158,
      "step": 2775
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.038419309888731e-05,
      "loss": 1.915,
      "step": 2776
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.0054971063952073e-05,
      "loss": 1.9042,
      "step": 2777
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.972680055152412e-05,
      "loss": 1.988,
      "step": 2778
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.9399681924865214e-05,
      "loss": 1.9804,
      "step": 2779
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.9073615546072815e-05,
      "loss": 1.8797,
      "step": 2780
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.8748601776079314e-05,
      "loss": 1.9306,
      "step": 2781
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.842464097465249e-05,
      "loss": 2.0169,
      "step": 2782
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.810173350039382e-05,
      "loss": 1.9419,
      "step": 2783
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.7779879710739385e-05,
      "loss": 1.934,
      "step": 2784
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.745907996195886e-05,
      "loss": 1.9162,
      "step": 2785
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.713933460915498e-05,
      "loss": 1.9396,
      "step": 2786
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.68206440062634e-05,
      "loss": 1.9558,
      "step": 2787
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.650300850605238e-05,
      "loss": 1.94,
      "step": 2788
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.6186428460122e-05,
      "loss": 1.9313,
      "step": 2789
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.587090421890405e-05,
      "loss": 1.9383,
      "step": 2790
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.5556436131661936e-05,
      "loss": 1.9954,
      "step": 2791
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.5243024546489767e-05,
      "loss": 1.9535,
      "step": 2792
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.493066981031213e-05,
      "loss": 1.9766,
      "step": 2793
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.4619372268884014e-05,
      "loss": 1.95,
      "step": 2794
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.430913226678957e-05,
      "loss": 1.9343,
      "step": 2795
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.3999950147442844e-05,
      "loss": 1.9701,
      "step": 2796
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.369182625308688e-05,
      "loss": 2.0039,
      "step": 2797
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.3384760924793156e-05,
      "loss": 1.9338,
      "step": 2798
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.3078754502461346e-05,
      "loss": 1.9252,
      "step": 2799
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.2773807324819394e-05,
      "loss": 1.9254,
      "step": 2800
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.2469919729422046e-05,
      "loss": 1.9186,
      "step": 2801
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.216709205265179e-05,
      "loss": 1.9861,
      "step": 2802
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.186532462971748e-05,
      "loss": 2.0021,
      "step": 2803
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.156461779465459e-05,
      "loss": 2.0414,
      "step": 2804
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.126497188032452e-05,
      "loss": 1.9514,
      "step": 2805
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.0966387218414167e-05,
      "loss": 1.9484,
      "step": 2806
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.0668864139436044e-05,
      "loss": 1.9023,
      "step": 2807
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.037240297272693e-05,
      "loss": 1.9755,
      "step": 2808
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.0077004046448875e-05,
      "loss": 2.0122,
      "step": 2809
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.978266768758754e-05,
      "loss": 1.9247,
      "step": 2810
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.9489394221952745e-05,
      "loss": 1.9427,
      "step": 2811
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.919718397417771e-05,
      "loss": 1.9143,
      "step": 2812
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.8906037267718686e-05,
      "loss": 1.8401,
      "step": 2813
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.861595442485444e-05,
      "loss": 1.8935,
      "step": 2814
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.832693576668644e-05,
      "loss": 1.9562,
      "step": 2815
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.803898161313812e-05,
      "loss": 1.9451,
      "step": 2816
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.77520922829544e-05,
      "loss": 2.0206,
      "step": 2817
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.7466268093701797e-05,
      "loss": 1.9718,
      "step": 2818
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.718150936176756e-05,
      "loss": 1.9156,
      "step": 2819
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.689781640235979e-05,
      "loss": 1.9306,
      "step": 2820
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.6615189529506375e-05,
      "loss": 1.9077,
      "step": 2821
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.633362905605564e-05,
      "loss": 1.9141,
      "step": 2822
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.6053135293675265e-05,
      "loss": 1.995,
      "step": 2823
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.577370855285211e-05,
      "loss": 2.0011,
      "step": 2824
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.54953491428921e-05,
      "loss": 1.9562,
      "step": 2825
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.521805737191941e-05,
      "loss": 1.9034,
      "step": 2826
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.494183354687675e-05,
      "loss": 2.0163,
      "step": 2827
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.4666677973524296e-05,
      "loss": 1.955,
      "step": 2828
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.439259095644009e-05,
      "loss": 1.9377,
      "step": 2829
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.411957279901934e-05,
      "loss": 1.9349,
      "step": 2830
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.384762380347384e-05,
      "loss": 1.9118,
      "step": 2831
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.3576744270832124e-05,
      "loss": 1.9248,
      "step": 2832
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.33069345009388e-05,
      "loss": 2.0115,
      "step": 2833
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.30381947924544e-05,
      "loss": 1.887,
      "step": 2834
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.2770525442854747e-05,
      "loss": 1.9422,
      "step": 2835
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.2503926748431275e-05,
      "loss": 1.952,
      "step": 2836
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.2238399004289934e-05,
      "loss": 1.9094,
      "step": 2837
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.197394250435137e-05,
      "loss": 1.9267,
      "step": 2838
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.171055754135022e-05,
      "loss": 2.0696,
      "step": 2839
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.144824440683536e-05,
      "loss": 2.0267,
      "step": 2840
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.118700339116887e-05,
      "loss": 1.9677,
      "step": 2841
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.09268347835262e-05,
      "loss": 1.9343,
      "step": 2842
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.0667738871896e-05,
      "loss": 2.0085,
      "step": 2843
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.0409715943078954e-05,
      "loss": 1.9525,
      "step": 2844
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.0152766282688705e-05,
      "loss": 1.9444,
      "step": 2845
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.9896890175150182e-05,
      "loss": 1.9569,
      "step": 2846
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.9642087903700264e-05,
      "loss": 1.9472,
      "step": 2847
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.938835975038745e-05,
      "loss": 2.0479,
      "step": 2848
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.913570599607085e-05,
      "loss": 1.945,
      "step": 2849
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8884126920420527e-05,
      "loss": 2.0412,
      "step": 2850
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8633622801916727e-05,
      "loss": 1.958,
      "step": 2851
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8384193917850078e-05,
      "loss": 1.9877,
      "step": 2852
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8135840544320725e-05,
      "loss": 1.9885,
      "step": 2853
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.788856295623854e-05,
      "loss": 1.9838,
      "step": 2854
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.764236142732246e-05,
      "loss": 1.9523,
      "step": 2855
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.7397236230100486e-05,
      "loss": 1.9038,
      "step": 2856
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.7153187635908573e-05,
      "loss": 1.9218,
      "step": 2857
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.6910215914891623e-05,
      "loss": 1.9446,
      "step": 2858
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.666832133600239e-05,
      "loss": 1.9376,
      "step": 2859
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.6427504167001014e-05,
      "loss": 1.9269,
      "step": 2860
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.6187764674455383e-05,
      "loss": 1.9506,
      "step": 2861
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.5949103123740214e-05,
      "loss": 1.9913,
      "step": 2862
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.5711519779037186e-05,
      "loss": 1.9349,
      "step": 2863
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.5475014903334147e-05,
      "loss": 1.9399,
      "step": 2864
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.523958875842569e-05,
      "loss": 1.8954,
      "step": 2865
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.500524160491191e-05,
      "loss": 2.0251,
      "step": 2866
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.4771973702198637e-05,
      "loss": 1.9348,
      "step": 2867
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.4539785308497098e-05,
      "loss": 1.9591,
      "step": 2868
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.4308676680823593e-05,
      "loss": 1.962,
      "step": 2869
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.4078648074999155e-05,
      "loss": 2.0041,
      "step": 2870
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.384969974564932e-05,
      "loss": 1.9846,
      "step": 2871
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.362183194620382e-05,
      "loss": 1.9603,
      "step": 2872
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.3395044928896214e-05,
      "loss": 1.9369,
      "step": 2873
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.3169338944764028e-05,
      "loss": 1.9638,
      "step": 2874
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.2944714243647746e-05,
      "loss": 1.8804,
      "step": 2875
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.272117107419136e-05,
      "loss": 1.9629,
      "step": 2876
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.2498709683841377e-05,
      "loss": 1.8778,
      "step": 2877
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.2277330318846823e-05,
      "loss": 1.9294,
      "step": 2878
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.2057033224259338e-05,
      "loss": 1.9699,
      "step": 2879
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1837818643932196e-05,
      "loss": 1.9177,
      "step": 2880
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1619686820520624e-05,
      "loss": 1.837,
      "step": 2881
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1402637995481257e-05,
      "loss": 1.9743,
      "step": 2882
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1186672409071904e-05,
      "loss": 1.9803,
      "step": 2883
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.0971790300351345e-05,
      "loss": 1.9381,
      "step": 2884
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.0757991907178974e-05,
      "loss": 2.0757,
      "step": 2885
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.0545277466214596e-05,
      "loss": 1.9608,
      "step": 2886
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.0333647212918194e-05,
      "loss": 1.9697,
      "step": 2887
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.0123101381549715e-05,
      "loss": 1.9546,
      "step": 2888
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9913640205168505e-05,
      "loss": 1.8987,
      "step": 2889
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.970526391563332e-05,
      "loss": 1.9115,
      "step": 2890
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.949797274360221e-05,
      "loss": 1.9835,
      "step": 2891
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.929176691853196e-05,
      "loss": 1.9922,
      "step": 2892
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9086646668677875e-05,
      "loss": 1.9453,
      "step": 2893
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8882612221093886e-05,
      "loss": 1.9429,
      "step": 2894
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8679663801631553e-05,
      "loss": 1.999,
      "step": 2895
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8477801634940618e-05,
      "loss": 1.993,
      "step": 2896
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.827702594446845e-05,
      "loss": 1.9524,
      "step": 2897
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.80773369524595e-05,
      "loss": 1.8849,
      "step": 2898
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7878734879955615e-05,
      "loss": 1.9341,
      "step": 2899
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7681219946795168e-05,
      "loss": 2.0376,
      "step": 2900
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7484792371613602e-05,
      "loss": 1.9532,
      "step": 2901
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7289452371842317e-05,
      "loss": 2.0101,
      "step": 2902
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7095200163708912e-05,
      "loss": 1.9608,
      "step": 2903
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.690203596223705e-05,
      "loss": 1.9451,
      "step": 2904
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6709959981245916e-05,
      "loss": 1.8723,
      "step": 2905
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.651897243335021e-05,
      "loss": 2.0041,
      "step": 2906
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6329073529959715e-05,
      "loss": 1.9579,
      "step": 2907
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.614026348127917e-05,
      "loss": 1.8972,
      "step": 2908
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.5952542496308064e-05,
      "loss": 1.917,
      "step": 2909
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5765910782840286e-05,
      "loss": 1.9624,
      "step": 2910
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.558036854746414e-05,
      "loss": 1.8962,
      "step": 2911
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5395915995561893e-05,
      "loss": 2.0248,
      "step": 2912
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5212553331309553e-05,
      "loss": 2.0107,
      "step": 2913
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5030280757676763e-05,
      "loss": 1.9053,
      "step": 2914
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4849098476426349e-05,
      "loss": 1.9775,
      "step": 2915
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.466900668811444e-05,
      "loss": 2.0041,
      "step": 2916
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4490005592090017e-05,
      "loss": 2.0069,
      "step": 2917
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4312095386494806e-05,
      "loss": 1.941,
      "step": 2918
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4135276268262942e-05,
      "loss": 2.0025,
      "step": 2919
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3959548433120638e-05,
      "loss": 1.9607,
      "step": 2920
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3784912075586408e-05,
      "loss": 1.953,
      "step": 2921
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3611367388970285e-05,
      "loss": 1.9768,
      "step": 2922
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3438914565374271e-05,
      "loss": 1.948,
      "step": 2923
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3267553795691334e-05,
      "loss": 2.0325,
      "step": 2924
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3097285269606074e-05,
      "loss": 1.9075,
      "step": 2925
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2928109175593617e-05,
      "loss": 1.9279,
      "step": 2926
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2760025700920164e-05,
      "loss": 1.9428,
      "step": 2927
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2593035031642109e-05,
      "loss": 1.9207,
      "step": 2928
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2427137352606588e-05,
      "loss": 1.9958,
      "step": 2929
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2262332847450708e-05,
      "loss": 1.9147,
      "step": 2930
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.209862169860132e-05,
      "loss": 1.9149,
      "step": 2931
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1936004087275464e-05,
      "loss": 1.9741,
      "step": 2932
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1774480193479265e-05,
      "loss": 1.966,
      "step": 2933
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1614050196008253e-05,
      "loss": 1.917,
      "step": 2934
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1454714272447264e-05,
      "loss": 1.9195,
      "step": 2935
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1296472599169993e-05,
      "loss": 1.9314,
      "step": 2936
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.113932535133888e-05,
      "loss": 1.9046,
      "step": 2937
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.098327270290489e-05,
      "loss": 1.8829,
      "step": 2938
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0828314826607511e-05,
      "loss": 1.9226,
      "step": 2939
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.067445189397398e-05,
      "loss": 2.0185,
      "step": 2940
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0521684075319837e-05,
      "loss": 1.903,
      "step": 2941
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.037001153974837e-05,
      "loss": 1.9517,
      "step": 2942
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.02194344551505e-05,
      "loss": 2.0394,
      "step": 2943
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0069952988204566e-05,
      "loss": 1.9713,
      "step": 2944
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.921567304375878e-06,
      "loss": 1.9695,
      "step": 2945
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.774277567916934e-06,
      "loss": 1.9287,
      "step": 2946
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.628083941867427e-06,
      "loss": 1.9801,
      "step": 2947
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.482986588053132e-06,
      "loss": 2.0046,
      "step": 2948
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.338985667086909e-06,
      "loss": 2.005,
      "step": 2949
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.196081338367468e-06,
      "loss": 1.8992,
      "step": 2950
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.054273760080057e-06,
      "loss": 1.946,
      "step": 2951
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.913563089195554e-06,
      "loss": 1.9397,
      "step": 2952
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.773949481470922e-06,
      "loss": 1.9271,
      "step": 2953
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.63543309144843e-06,
      "loss": 2.0136,
      "step": 2954
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.498014072456317e-06,
      "loss": 1.9567,
      "step": 2955
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.361692576607572e-06,
      "loss": 1.9173,
      "step": 2956
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.226468754800598e-06,
      "loss": 1.9936,
      "step": 2957
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.092342756718663e-06,
      "loss": 1.9795,
      "step": 2958
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.959314730829781e-06,
      "loss": 1.9711,
      "step": 2959
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.827384824386719e-06,
      "loss": 2.006,
      "step": 2960
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.696553183426658e-06,
      "loss": 1.9886,
      "step": 2961
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.566819952770976e-06,
      "loss": 1.9043,
      "step": 2962
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.438185276025245e-06,
      "loss": 1.968,
      "step": 2963
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.3106492955792305e-06,
      "loss": 2.0478,
      "step": 2964
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.184212152606007e-06,
      "loss": 1.9047,
      "step": 2965
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.0588739870628414e-06,
      "loss": 1.9509,
      "step": 2966
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.9346349376901985e-06,
      "loss": 1.9693,
      "step": 2967
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.811495142011959e-06,
      "loss": 1.9863,
      "step": 2968
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.68945473633531e-06,
      "loss": 1.8908,
      "step": 2969
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.568513855750524e-06,
      "loss": 1.9813,
      "step": 2970
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.4486726341304035e-06,
      "loss": 1.9178,
      "step": 2971
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.329931204130946e-06,
      "loss": 1.9719,
      "step": 2972
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.2122896971905655e-06,
      "loss": 2.0168,
      "step": 2973
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.095748243530097e-06,
      "loss": 1.933,
      "step": 2974
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.980306972152904e-06,
      "loss": 1.9662,
      "step": 2975
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.8659660108442144e-06,
      "loss": 1.9866,
      "step": 2976
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.752725486171562e-06,
      "loss": 1.9492,
      "step": 2977
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.640585523484232e-06,
      "loss": 1.8969,
      "step": 2978
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.529546246913153e-06,
      "loss": 1.9138,
      "step": 2979
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.4196077793712276e-06,
      "loss": 1.9064,
      "step": 2980
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.310770242552554e-06,
      "loss": 1.9509,
      "step": 2981
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.203033756932651e-06,
      "loss": 1.9821,
      "step": 2982
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.096398441768235e-06,
      "loss": 1.9687,
      "step": 2983
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.990864415097107e-06,
      "loss": 1.9153,
      "step": 2984
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.886431793737933e-06,
      "loss": 1.9426,
      "step": 2985
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.783100693290576e-06,
      "loss": 2.0313,
      "step": 2986
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.680871228135097e-06,
      "loss": 2.048,
      "step": 2987
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.579743511432311e-06,
      "loss": 1.9879,
      "step": 2988
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.479717655123783e-06,
      "loss": 1.9707,
      "step": 2989
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.380793769930724e-06,
      "loss": 1.959,
      "step": 2990
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.282971965355209e-06,
      "loss": 1.9527,
      "step": 2991
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.186252349679065e-06,
      "loss": 1.9886,
      "step": 2992
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.090635029964096e-06,
      "loss": 1.9049,
      "step": 2993
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.99612011205197e-06,
      "loss": 1.9113,
      "step": 2994
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.902707700564112e-06,
      "loss": 1.9994,
      "step": 2995
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.810397898901363e-06,
      "loss": 1.9225,
      "step": 2996
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.7191908092444324e-06,
      "loss": 2.0016,
      "step": 2997
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.6290865325528944e-06,
      "loss": 1.9885,
      "step": 2998
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.540085168566076e-06,
      "loss": 2.0084,
      "step": 2999
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.452186815802172e-06,
      "loss": 1.9864,
      "step": 3000
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.3653915715585738e-06,
      "loss": 1.9354,
      "step": 3001
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.2796995319113175e-06,
      "loss": 2.0404,
      "step": 3002
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.1951107917156386e-06,
      "loss": 1.928,
      "step": 3003
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.111625444605415e-06,
      "loss": 1.9209,
      "step": 3004
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.0292435829928353e-06,
      "loss": 1.9178,
      "step": 3005
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.9479652980690663e-06,
      "loss": 1.9522,
      "step": 3006
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.8677906798033617e-06,
      "loss": 1.8929,
      "step": 3007
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.788719816943397e-06,
      "loss": 1.9711,
      "step": 3008
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.710752797015159e-06,
      "loss": 1.9309,
      "step": 3009
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.633889706322501e-06,
      "loss": 1.9784,
      "step": 3010
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.558130629947586e-06,
      "loss": 1.982,
      "step": 3011
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.483475651750333e-06,
      "loss": 1.9541,
      "step": 3012
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.40992485436875e-06,
      "loss": 1.9719,
      "step": 3013
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.3374783192181558e-06,
      "loss": 1.8735,
      "step": 3014
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.2661361264919578e-06,
      "loss": 1.9724,
      "step": 3015
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.1958983551608745e-06,
      "loss": 1.8659,
      "step": 3016
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.126765082973159e-06,
      "loss": 1.96,
      "step": 3017
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.058736386454596e-06,
      "loss": 1.9726,
      "step": 3018
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.9918123409081722e-06,
      "loss": 1.9338,
      "step": 3019
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.925993020414074e-06,
      "loss": 1.965,
      "step": 3020
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.8612784978295772e-06,
      "loss": 1.9482,
      "step": 3021
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.7976688447892687e-06,
      "loss": 1.9501,
      "step": 3022
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.7351641317044918e-06,
      "loss": 1.9503,
      "step": 3023
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.6737644277636798e-06,
      "loss": 1.9754,
      "step": 3024
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.6134698009317994e-06,
      "loss": 2.0034,
      "step": 3025
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.5542803179510178e-06,
      "loss": 1.9807,
      "step": 3026
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.4961960443398148e-06,
      "loss": 1.9134,
      "step": 3027
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.439217044393315e-06,
      "loss": 2.0051,
      "step": 3028
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3833433811833994e-06,
      "loss": 1.944,
      "step": 3029
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3285751165583726e-06,
      "loss": 1.9237,
      "step": 3030
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.2749123111426286e-06,
      "loss": 1.9679,
      "step": 3031
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.2223550243372073e-06,
      "loss": 1.9734,
      "step": 3032
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.1709033143195714e-06,
      "loss": 2.0292,
      "step": 3033
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.1205572380428298e-06,
      "loss": 1.9776,
      "step": 3034
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0713168512366257e-06,
      "loss": 1.9633,
      "step": 3035
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0231822084068033e-06,
      "loss": 1.9171,
      "step": 3036
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.76153362834853e-07,
      "loss": 1.9936,
      "step": 3037
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.302303665785772e-07,
      "loss": 1.9881,
      "step": 3038
    },
    {
      "epoch": 0.99,
      "learning_rate": 8.854132704713136e-07,
      "loss": 2.0263,
      "step": 3039
    },
    {
      "epoch": 0.99,
      "learning_rate": 8.417021241224899e-07,
      "loss": 1.9965,
      "step": 3040
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.990969759174016e-07,
      "loss": 1.9417,
      "step": 3041
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.575978730167688e-07,
      "loss": 2.0792,
      "step": 3042
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.172048613574012e-07,
      "loss": 1.8986,
      "step": 3043
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.779179856514217e-07,
      "loss": 1.9614,
      "step": 3044
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.397372893865993e-07,
      "loss": 1.944,
      "step": 3045
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.026628148263491e-07,
      "loss": 2.0125,
      "step": 3046
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.666946030095099e-07,
      "loss": 1.8974,
      "step": 3047
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.318326937503448e-07,
      "loss": 1.9212,
      "step": 3048
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.980771256385408e-07,
      "loss": 2.0016,
      "step": 3049
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.654279360392089e-07,
      "loss": 1.9803,
      "step": 3050
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.3388516109266196e-07,
      "loss": 2.0401,
      "step": 3051
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.0344883571452606e-07,
      "loss": 1.9063,
      "step": 3052
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.741189935956291e-07,
      "loss": 1.9398,
      "step": 3053
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.4589566720211185e-07,
      "loss": 2.0023,
      "step": 3054
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.1877888777531725e-07,
      "loss": 1.9799,
      "step": 3055
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.9276868533145706e-07,
      "loss": 1.9627,
      "step": 3056
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.6786508866205593e-07,
      "loss": 1.9419,
      "step": 3057
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.4406812533361855e-07,
      "loss": 1.9866,
      "step": 3058
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.2137782168785147e-07,
      "loss": 1.9632,
      "step": 3059
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.9979420284110815e-07,
      "loss": 1.9604,
      "step": 3060
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.7931729268505504e-07,
      "loss": 1.9185,
      "step": 3061
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.599471138862274e-07,
      "loss": 1.9139,
      "step": 3062
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.416836878861405e-07,
      "loss": 2.0092,
      "step": 3063
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.2452703490084538e-07,
      "loss": 1.9322,
      "step": 3064
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0847717392181711e-07,
      "loss": 1.8879,
      "step": 3065
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.353412271495554e-08,
      "loss": 1.9738,
      "step": 3066
    },
    {
      "epoch": 1.0,
      "learning_rate": 7.969789782125147e-08,
      "loss": 1.8862,
      "step": 3067
    },
    {
      "epoch": 1.0,
      "learning_rate": 6.696851455645359e-08,
      "loss": 1.9788,
      "step": 3068
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.534598701106841e-08,
      "loss": 1.8941,
      "step": 3069
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.483032805047138e-08,
      "loss": 1.8734,
      "step": 3070
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.542154931457375e-08,
      "loss": 1.994,
      "step": 3071
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.7119661218488746e-08,
      "loss": 1.9776,
      "step": 3072
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.9924672951643352e-08,
      "loss": 1.9884,
      "step": 3073
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.3836592478444488e-08,
      "loss": 1.9403,
      "step": 3074
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.85542653794591e-09,
      "loss": 1.9776,
      "step": 3075
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.981180643959249e-09,
      "loss": 1.9452,
      "step": 3076
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.213859085054004e-09,
      "loss": 1.9349,
      "step": 3077
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.534649244465229e-10,
      "loss": 2.0038,
      "step": 3078
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.8175,
      "step": 3079
    },
    {
      "epoch": 1.0,
      "step": 3079,
      "total_flos": 2.140960418532478e+19,
      "train_loss": 2.030868922049599,
      "train_runtime": 25336.8024,
      "train_samples_per_second": 15.551,
      "train_steps_per_second": 0.122
    }
  ],
  "max_steps": 3079,
  "num_train_epochs": 1,
  "total_flos": 2.140960418532478e+19,
  "trial_name": null,
  "trial_params": null
}