{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 1014,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 6.451612903225806e-06,
      "loss": 0.1129,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.2903225806451613e-05,
      "loss": 0.2075,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.935483870967742e-05,
      "loss": 0.2,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.5806451612903226e-05,
      "loss": 0.1129,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.2258064516129034e-05,
      "loss": 0.1462,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.870967741935484e-05,
      "loss": 0.1246,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.516129032258064e-05,
      "loss": 0.0955,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.161290322580645e-05,
      "loss": 0.0836,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.8064516129032266e-05,
      "loss": 0.0858,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.451612903225807e-05,
      "loss": 0.0999,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.096774193548388e-05,
      "loss": 0.061,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.741935483870968e-05,
      "loss": 0.063,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.387096774193549e-05,
      "loss": 0.0535,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.032258064516129e-05,
      "loss": 0.0784,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.677419354838711e-05,
      "loss": 0.1076,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001032258064516129,
      "loss": 0.0906,
      "step": 16
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010967741935483871,
      "loss": 0.0865,
      "step": 17
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011612903225806453,
      "loss": 0.0596,
      "step": 18
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012258064516129034,
      "loss": 0.0933,
      "step": 19
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012903225806451613,
      "loss": 0.0638,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013548387096774193,
      "loss": 0.1095,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014193548387096775,
      "loss": 0.0548,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014838709677419355,
      "loss": 0.0709,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015483870967741937,
      "loss": 0.0691,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016129032258064516,
      "loss": 0.0586,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00016774193548387098,
      "loss": 0.0631,
      "step": 26
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00017419354838709678,
      "loss": 0.0606,
      "step": 27
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018064516129032257,
      "loss": 0.0825,
      "step": 28
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001870967741935484,
      "loss": 0.0313,
      "step": 29
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019354838709677422,
      "loss": 0.0438,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.0662,
      "step": 31
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999948930413158,
      "loss": 0.1139,
      "step": 32
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999795722174243,
      "loss": 0.0644,
      "step": 33
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999540376848117,
      "loss": 0.0836,
      "step": 34
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999182897042857,
      "loss": 0.0507,
      "step": 35
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999872328640973,
      "loss": 0.0576,
      "step": 36
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999816154964316,
      "loss": 0.0597,
      "step": 37
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999749769248068,
      "loss": 0.1041,
      "step": 38
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019996731721702875,
      "loss": 0.0398,
      "step": 39
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019995863645133307,
      "loss": 0.0721,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019994893471638432,
      "loss": 0.0407,
      "step": 41
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999382121112753,
      "loss": 0.1591,
      "step": 42
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019992646874552578,
      "loss": 0.0404,
      "step": 43
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999137047390815,
      "loss": 0.0728,
      "step": 44
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019989992022231303,
      "loss": 0.025,
      "step": 45
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019988511533601425,
      "loss": 0.0897,
      "step": 46
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000199869290231401,
      "loss": 0.0528,
      "step": 47
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019985244507010968,
      "loss": 0.0384,
      "step": 48
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019983458002419534,
      "loss": 0.1167,
      "step": 49
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019981569527613004,
      "loss": 0.1163,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001997957910188011,
      "loss": 0.1524,
      "step": 51
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001997748674555089,
      "loss": 0.0568,
      "step": 52
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019975292479996502,
      "loss": 0.0964,
      "step": 53
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019972996327628995,
      "loss": 0.0757,
      "step": 54
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019970598311901076,
      "loss": 0.0522,
      "step": 55
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001996809845730588,
      "loss": 0.0124,
      "step": 56
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019965496789376718,
      "loss": 0.0804,
      "step": 57
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001996279333468681,
      "loss": 0.0659,
      "step": 58
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019959988120849014,
      "loss": 0.067,
      "step": 59
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001995708117651556,
      "loss": 0.1222,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019954072531377733,
      "loss": 0.0618,
      "step": 61
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019950962216165586,
      "loss": 0.0652,
      "step": 62
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001994775026264762,
      "loss": 0.1025,
      "step": 63
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019944436703630468,
      "loss": 0.0764,
      "step": 64
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019941021572958544,
      "loss": 0.0553,
      "step": 65
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001993750490551371,
      "loss": 0.069,
      "step": 66
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001993388673721492,
      "loss": 0.0841,
      "step": 67
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019930167105017843,
      "loss": 0.0244,
      "step": 68
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019926346046914497,
      "loss": 0.0499,
      "step": 69
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019922423601932853,
      "loss": 0.0339,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019918399810136438,
      "loss": 0.0607,
      "step": 71
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001991427471262393,
      "loss": 0.046,
      "step": 72
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001991004835152874,
      "loss": 0.1192,
      "step": 73
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001990572077001856,
      "loss": 0.0888,
      "step": 74
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019901292012294955,
      "loss": 0.0402,
      "step": 75
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019896762123592895,
      "loss": 0.0915,
      "step": 76
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019892131150180283,
      "loss": 0.0385,
      "step": 77
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000198873991393575,
      "loss": 0.0663,
      "step": 78
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019882566139456915,
      "loss": 0.0389,
      "step": 79
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019877632199842392,
      "loss": 0.0519,
      "step": 80
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019872597370908777,
      "loss": 0.0515,
      "step": 81
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019867461704081398,
      "loss": 0.0713,
      "step": 82
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019862225251815534,
      "loss": 0.0375,
      "step": 83
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019856888067595874,
      "loss": 0.0639,
      "step": 84
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019851450205935977,
      "loss": 0.0597,
      "step": 85
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019845911722377713,
      "loss": 0.0269,
      "step": 86
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019840272673490693,
      "loss": 0.0421,
      "step": 87
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019834533116871704,
      "loss": 0.0799,
      "step": 88
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019828693111144095,
      "loss": 0.0519,
      "step": 89
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019822752715957203,
      "loss": 0.1014,
      "step": 90
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019816711991985737,
      "loss": 0.0451,
      "step": 91
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019810571000929147,
      "loss": 0.1064,
      "step": 92
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019804329805511018,
      "loss": 0.0545,
      "step": 93
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001979798846947839,
      "loss": 0.077,
      "step": 94
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019791547057601162,
      "loss": 0.0317,
      "step": 95
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001978500563567137,
      "loss": 0.0389,
      "step": 96
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019778364270502558,
      "loss": 0.0355,
      "step": 97
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019771623029929088,
      "loss": 0.0738,
      "step": 98
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019764781982805428,
      "loss": 0.0411,
      "step": 99
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019757841199005474,
      "loss": 0.1486,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019750800749421813,
      "loss": 0.0476,
      "step": 101
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019743660705965016,
      "loss": 0.0452,
      "step": 102
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019736421141562896,
      "loss": 0.0658,
      "step": 103
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019729082130159767,
      "loss": 0.0979,
      "step": 104
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019721643746715688,
      "loss": 0.0517,
      "step": 105
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001971410606720569,
      "loss": 0.0838,
      "step": 106
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001970646916861901,
      "loss": 0.0204,
      "step": 107
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019698733128958295,
      "loss": 0.0198,
      "step": 108
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001969089802723882,
      "loss": 0.0208,
      "step": 109
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001968296394348766,
      "loss": 0.0265,
      "step": 110
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000196749309587429,
      "loss": 0.13,
      "step": 111
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019666799155052778,
      "loss": 0.0808,
      "step": 112
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019658568615474862,
      "loss": 0.0651,
      "step": 113
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019650239424075206,
      "loss": 0.1267,
      "step": 114
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019641811665927484,
      "loss": 0.0508,
      "step": 115
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019633285427112117,
      "loss": 0.047,
      "step": 116
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019624660794715412,
      "loss": 0.1234,
      "step": 117
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001961593785682864,
      "loss": 0.0354,
      "step": 118
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019607116702547174,
      "loss": 0.0449,
      "step": 119
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001959819742196956,
      "loss": 0.0578,
      "step": 120
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019589180106196582,
      "loss": 0.031,
      "step": 121
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001958006484733037,
      "loss": 0.0794,
      "step": 122
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019570851738473413,
      "loss": 0.0372,
      "step": 123
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019561540873727653,
      "loss": 0.0164,
      "step": 124
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019552132348193486,
      "loss": 0.0165,
      "step": 125
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001954262625796882,
      "loss": 0.0886,
      "step": 126
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019533022700148072,
      "loss": 0.4116,
      "step": 127
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001952332177282119,
      "loss": 0.0364,
      "step": 128
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019513523575072643,
      "loss": 0.1257,
      "step": 129
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019503628206980414,
      "loss": 0.0788,
      "step": 130
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001949363576961497,
      "loss": 0.0638,
      "step": 131
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019483546365038247,
      "loss": 0.0503,
      "step": 132
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001947336009630259,
      "loss": 0.0863,
      "step": 133
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000194630770674497,
      "loss": 0.0494,
      "step": 134
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019452697383509588,
      "loss": 0.0339,
      "step": 135
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019442221150499492,
      "loss": 0.0474,
      "step": 136
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019431648475422782,
      "loss": 0.0188,
      "step": 137
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001942097946626789,
      "loss": 0.0364,
      "step": 138
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019410214232007197,
      "loss": 0.0616,
      "step": 139
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019399352882595915,
      "loss": 0.0224,
      "step": 140
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001938839552897097,
      "loss": 0.0276,
      "step": 141
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019377342283049864,
      "loss": 0.0419,
      "step": 142
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001936619325772954,
      "loss": 0.0672,
      "step": 143
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001935494856688522,
      "loss": 0.3356,
      "step": 144
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019343608325369247,
      "loss": 0.6535,
      "step": 145
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019332172649009913,
      "loss": 0.2866,
      "step": 146
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019320641654610267,
      "loss": 0.2056,
      "step": 147
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019309015459946939,
      "loss": 0.2119,
      "step": 148
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019297294183768916,
      "loss": 0.1324,
      "step": 149
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019285477945796346,
      "loss": 0.056,
      "step": 150
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019273566866719307,
      "loss": 0.1161,
      "step": 151
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019261561068196573,
      "loss": 0.1027,
      "step": 152
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019249460672854387,
      "loss": 0.0439,
      "step": 153
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019237265804285177,
      "loss": 0.0981,
      "step": 154
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019224976587046332,
      "loss": 0.1057,
      "step": 155
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001921259314665889,
      "loss": 0.0461,
      "step": 156
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019200115609606302,
      "loss": 0.0778,
      "step": 157
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001918754410333309,
      "loss": 0.096,
      "step": 158
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019174878756243583,
      "loss": 0.1929,
      "step": 159
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019162119697700591,
      "loss": 0.0839,
      "step": 160
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019149267058024083,
      "loss": 0.0642,
      "step": 161
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019136320968489857,
      "loss": 0.0662,
      "step": 162
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019123281561328205,
      "loss": 0.0737,
      "step": 163
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001911014896972255,
      "loss": 0.0406,
      "step": 164
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019096923327808102,
      "loss": 0.0555,
      "step": 165
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019083604770670472,
      "loss": 0.0594,
      "step": 166
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019070193434344302,
      "loss": 0.0646,
      "step": 167
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019056689455811875,
      "loss": 0.0762,
      "step": 168
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019043092973001707,
      "loss": 0.0365,
      "step": 169
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019029404124787158,
      "loss": 0.0312,
      "step": 170
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019015623050984984,
      "loss": 0.029,
      "step": 171
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019001749892353943,
      "loss": 0.0742,
      "step": 172
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018987784790593324,
      "loss": 0.0951,
      "step": 173
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001897372788834152,
      "loss": 0.0388,
      "step": 174
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001895957932917458,
      "loss": 0.0117,
      "step": 175
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018945339257604707,
      "loss": 0.039,
      "step": 176
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018931007819078825,
      "loss": 0.0446,
      "step": 177
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018916585159977053,
      "loss": 0.0597,
      "step": 178
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018902071427611246,
      "loss": 0.0613,
      "step": 179
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018887466770223466,
      "loss": 0.0382,
      "step": 180
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018872771336984477,
      "loss": 0.0617,
      "step": 181
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018857985277992217,
      "loss": 0.0397,
      "step": 182
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018843108744270274,
      "loss": 0.0425,
      "step": 183
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018828141887766332,
      "loss": 0.0646,
      "step": 184
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018813084861350626,
      "loss": 0.0491,
      "step": 185
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018797937818814384,
      "loss": 0.0357,
      "step": 186
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018782700914868244,
      "loss": 0.031,
      "step": 187
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018767374305140683,
      "loss": 0.0133,
      "step": 188
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018751958146176424,
      "loss": 0.0269,
      "step": 189
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001873645259543485,
      "loss": 0.0465,
      "step": 190
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018720857811288362,
      "loss": 0.3442,
      "step": 191
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001870517395302081,
      "loss": 0.0119,
      "step": 192
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018689401180825815,
      "loss": 0.0392,
      "step": 193
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018673539655805174,
      "loss": 0.0133,
      "step": 194
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018657589539967196,
      "loss": 0.0619,
      "step": 195
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001864155099622504,
      "loss": 0.0453,
      "step": 196
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001862542418839507,
      "loss": 0.0628,
      "step": 197
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001860920928119517,
      "loss": 0.0285,
      "step": 198
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018592906440243061,
      "loss": 0.0371,
      "step": 199
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001857651583205461,
      "loss": 0.0465,
      "step": 200
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001856003762404214,
      "loss": 0.0442,
      "step": 201
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000185434719845127,
      "loss": 0.0546,
      "step": 202
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018526819082666368,
      "loss": 0.0667,
      "step": 203
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018510079088594509,
      "loss": 0.0277,
      "step": 204
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018493252173278033,
      "loss": 0.026,
      "step": 205
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018476338508585665,
      "loss": 0.045,
      "step": 206
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018459338267272184,
      "loss": 0.0179,
      "step": 207
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001844225162297664,
      "loss": 0.0399,
      "step": 208
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018425078750220614,
      "loss": 0.0647,
      "step": 209
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018407819824406408,
      "loss": 0.0235,
      "step": 210
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001839047502181526,
      "loss": 0.0365,
      "step": 211
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001837304451960556,
      "loss": 0.0586,
      "step": 212
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018355528495811005,
      "loss": 0.0216,
      "step": 213
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001833792712933882,
      "loss": 0.0477,
      "step": 214
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001832024059996791,
      "loss": 0.4065,
      "step": 215
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001830246908834702,
      "loss": 0.0568,
      "step": 216
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018284612775992906,
      "loss": 0.0383,
      "step": 217
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018266671845288464,
      "loss": 0.0467,
      "step": 218
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001824864647948088,
      "loss": 0.0256,
      "step": 219
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018230536862679747,
      "loss": 0.0341,
      "step": 220
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000182123431798552,
      "loss": 0.042,
      "step": 221
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018194065616836008,
      "loss": 0.0376,
      "step": 222
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018175704360307688,
      "loss": 0.0331,
      "step": 223
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018157259597810602,
      "loss": 0.0188,
      "step": 224
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018138731517738026,
      "loss": 0.0229,
      "step": 225
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018120120309334238,
      "loss": 0.0726,
      "step": 226
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018101426162692587,
      "loss": 0.0887,
      "step": 227
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018082649268753542,
      "loss": 0.0735,
      "step": 228
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001806378981930274,
      "loss": 0.03,
      "step": 229
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018044848006969048,
      "loss": 0.0451,
      "step": 230
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018025824025222565,
      "loss": 0.0394,
      "step": 231
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018006718068372672,
      "loss": 0.0399,
      "step": 232
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001798753033156603,
      "loss": 0.0089,
      "step": 233
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017968261010784602,
      "loss": 0.016,
      "step": 234
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017948910302843638,
      "loss": 0.2229,
      "step": 235
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017929478405389663,
      "loss": 0.5365,
      "step": 236
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001790996551689848,
      "loss": 1.8367,
      "step": 237
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017890371836673118,
      "loss": 0.2386,
      "step": 238
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017870697564841803,
      "loss": 0.1373,
      "step": 239
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017850942902355928,
      "loss": 0.2789,
      "step": 240
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017831108050987978,
      "loss": 0.0838,
      "step": 241
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001781119321332949,
      "loss": 0.047,
      "step": 242
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017791198592788967,
      "loss": 0.0346,
      "step": 243
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017771124393589814,
      "loss": 0.0278,
      "step": 244
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001775097082076824,
      "loss": 0.0377,
      "step": 245
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017730738080171175,
      "loss": 0.0399,
      "step": 246
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001771042637845416,
      "loss": 0.0213,
      "step": 247
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017690035923079235,
      "loss": 0.0332,
      "step": 248
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017669566922312826,
      "loss": 0.0266,
      "step": 249
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017649019585223622,
      "loss": 0.0156,
      "step": 250
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017628394121680415,
      "loss": 0.0262,
      "step": 251
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017607690742349995,
      "loss": 0.1003,
      "step": 252
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017586909658694967,
      "loss": 0.0629,
      "step": 253
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017566051082971597,
      "loss": 0.0634,
      "step": 254
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017545115228227655,
      "loss": 0.0339,
      "step": 255
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017524102308300236,
      "loss": 0.0232,
      "step": 256
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017503012537813564,
      "loss": 0.0732,
      "step": 257
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017481846132176815,
      "loss": 0.0676,
      "step": 258
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017460603307581902,
      "loss": 0.0404,
      "step": 259
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017439284281001285,
      "loss": 0.0611,
      "step": 260
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017417889270185735,
      "loss": 0.0554,
      "step": 261
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017396418493662133,
      "loss": 0.0591,
      "step": 262
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017374872170731207,
      "loss": 0.0524,
      "step": 263
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017353250521465324,
      "loss": 0.0682,
      "step": 264
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017331553766706224,
      "loss": 1.7005,
      "step": 265
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017309782128062764,
      "loss": 0.0843,
      "step": 266
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017287935827908662,
      "loss": 1.3616,
      "step": 267
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017266015089380224,
      "loss": 0.0807,
      "step": 268
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017244020136374065,
      "loss": 0.4651,
      "step": 269
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001722195119354481,
      "loss": 0.1874,
      "step": 270
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017199808486302823,
      "loss": 0.2203,
      "step": 271
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001717759224081189,
      "loss": 0.148,
      "step": 272
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017155302683986894,
      "loss": 0.1682,
      "step": 273
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017132940043491538,
      "loss": 0.0387,
      "step": 274
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017110504547735982,
      "loss": 0.0393,
      "step": 275
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017087996425874523,
      "loss": 0.0585,
      "step": 276
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017065415907803258,
      "loss": 0.1035,
      "step": 277
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017042763224157733,
      "loss": 0.0974,
      "step": 278
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001702003860631059,
      "loss": 0.072,
      "step": 279
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016997242286369196,
      "loss": 0.0506,
      "step": 280
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016974374497173277,
      "loss": 0.1191,
      "step": 281
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016951435472292543,
      "loss": 0.1262,
      "step": 282
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016928425446024304,
      "loss": 0.0686,
      "step": 283
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001690534465339106,
      "loss": 0.0656,
      "step": 284
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016882193330138124,
      "loss": 0.0502,
      "step": 285
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016858971712731196,
      "loss": 0.0332,
      "step": 286
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016835680038353957,
      "loss": 0.0553,
      "step": 287
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001681231854490565,
      "loss": 0.2367,
      "step": 288
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016788887470998632,
      "loss": 0.0867,
      "step": 289
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016765387055955958,
      "loss": 0.0284,
      "step": 290
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016741817539808927,
      "loss": 0.0891,
      "step": 291
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016718179163294629,
      "loss": 0.1499,
      "step": 292
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016694472167853486,
      "loss": 0.1557,
      "step": 293
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016670696795626793,
      "loss": 5.755,
      "step": 294
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016646853289454237,
      "loss": 2.6485,
      "step": 295
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016622941892871417,
      "loss": 1.1198,
      "step": 296
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016598962850107368,
      "loss": 0.2973,
      "step": 297
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016574916406082043,
      "loss": 0.3,
      "step": 298
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016550802806403843,
      "loss": 0.0799,
      "step": 299
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016526622297367076,
      "loss": 0.0629,
      "step": 300
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016502375125949467,
      "loss": 0.0906,
      "step": 301
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001647806153980962,
      "loss": 0.0538,
      "step": 302
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016453681787284493,
      "loss": 0.0623,
      "step": 303
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016429236117386866,
      "loss": 0.0249,
      "step": 304
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001640472477980279,
      "loss": 0.104,
      "step": 305
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016380148024889047,
      "loss": 0.0917,
      "step": 306
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016355506103670573,
      "loss": 0.0315,
      "step": 307
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001633079926783792,
      "loss": 0.05,
      "step": 308
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016306027769744666,
      "loss": 0.0118,
      "step": 309
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016281191862404842,
      "loss": 0.0436,
      "step": 310
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001625629179949036,
      "loss": 0.0405,
      "step": 311
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016231327835328406,
      "loss": 0.0233,
      "step": 312
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001620630022489884,
      "loss": 0.0998,
      "step": 313
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016181209223831614,
      "loss": 0.036,
      "step": 314
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016156055088404128,
      "loss": 0.0296,
      "step": 315
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016130838075538654,
      "loss": 0.1588,
      "step": 316
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016105558442799676,
      "loss": 0.0197,
      "step": 317
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016080216448391275,
      "loss": 0.064,
      "step": 318
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001605481235115448,
      "loss": 0.0335,
      "step": 319
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016029346410564648,
      "loss": 0.0359,
      "step": 320
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001600381888672879,
      "loss": 0.0599,
      "step": 321
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015978230040382925,
      "loss": 0.0445,
      "step": 322
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015952580132889415,
      "loss": 0.0663,
      "step": 323
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015926869426234296,
      "loss": 0.1002,
      "step": 324
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015901098183024602,
      "loss": 0.0853,
      "step": 325
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001587526666648568,
      "loss": 0.057,
      "step": 326
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015849375140458504,
      "loss": 0.0328,
      "step": 327
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015823423869396988,
      "loss": 0.1314,
      "step": 328
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015797413118365266,
      "loss": 0.0366,
      "step": 329
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015771343153034997,
      "loss": 0.0403,
      "step": 330
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015745214239682657,
      "loss": 0.0395,
      "step": 331
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015719026645186806,
      "loss": 0.0415,
      "step": 332
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015692780637025367,
      "loss": 0.0373,
      "step": 333
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015666476483272907,
      "loss": 0.0555,
      "step": 334
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015640114452597872,
      "loss": 0.0173,
      "step": 335
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015613694814259866,
      "loss": 0.0586,
      "step": 336
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015587217838106896,
      "loss": 0.0505,
      "step": 337
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015560683794572602,
      "loss": 0.146,
      "step": 338
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015534092954673517,
      "loss": 0.0842,
      "step": 339
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015507445590006285,
      "loss": 0.0109,
      "step": 340
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015480741972744876,
      "loss": 0.0508,
      "step": 341
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015453982375637844,
      "loss": 0.0414,
      "step": 342
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001542716707200549,
      "loss": 0.0807,
      "step": 343
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015400296335737118,
      "loss": 0.0537,
      "step": 344
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015373370441288206,
      "loss": 0.073,
      "step": 345
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015346389663677614,
      "loss": 0.0284,
      "step": 346
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015319354278484773,
      "loss": 0.0164,
      "step": 347
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015292264561846879,
      "loss": 0.0179,
      "step": 348
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015265120790456052,
      "loss": 0.0321,
      "step": 349
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015237923241556538,
      "loss": 0.0404,
      "step": 350
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015210672192941845,
      "loss": 0.0637,
      "step": 351
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001518336792295194,
      "loss": 0.0503,
      "step": 352
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015156010710470381,
      "loss": 0.04,
      "step": 353
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015128600834921467,
      "loss": 0.0435,
      "step": 354
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015101138576267408,
      "loss": 0.0186,
      "step": 355
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015073624215005446,
      "loss": 0.0284,
      "step": 356
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015046058032164989,
      "loss": 0.0122,
      "step": 357
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015018440309304753,
      "loss": 0.043,
      "step": 358
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00014990771328509878,
      "loss": 0.011,
      "step": 359
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014963051372389046,
      "loss": 0.0251,
      "step": 360
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014935280724071598,
      "loss": 0.04,
      "step": 361
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014907459667204642,
      "loss": 0.0805,
      "step": 362
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014879588485950155,
      "loss": 0.0073,
      "step": 363
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014851667464982078,
      "loss": 0.0333,
      "step": 364
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014823696889483415,
      "loss": 0.0079,
      "step": 365
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014795677045143304,
      "loss": 0.0082,
      "step": 366
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014767608218154132,
      "loss": 0.0216,
      "step": 367
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001473949069520857,
      "loss": 0.0594,
      "step": 368
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014711324763496674,
      "loss": 0.0152,
      "step": 369
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001468311071070295,
      "loss": 0.0468,
      "step": 370
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014654848825003394,
      "loss": 0.0255,
      "step": 371
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014626539395062578,
      "loss": 0.0289,
      "step": 372
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014598182710030673,
      "loss": 0.0284,
      "step": 373
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014569779059540522,
      "loss": 0.0298,
      "step": 374
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014541328733704665,
      "loss": 0.0458,
      "step": 375
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014512832023112375,
      "loss": 0.0404,
      "step": 376
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000144842892188267,
      "loss": 0.0334,
      "step": 377
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014455700612381488,
      "loss": 0.0437,
      "step": 378
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000144270664957784,
      "loss": 0.0314,
      "step": 379
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014398387161483937,
      "loss": 0.0659,
      "step": 380
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014369662902426452,
      "loss": 0.0109,
      "step": 381
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001434089401199315,
      "loss": 0.0085,
      "step": 382
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014312080784027102,
      "loss": 0.0415,
      "step": 383
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001428322351282424,
      "loss": 0.038,
      "step": 384
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014254322493130342,
      "loss": 0.0402,
      "step": 385
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014225378020138042,
      "loss": 0.0153,
      "step": 386
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014196390389483788,
      "loss": 0.0215,
      "step": 387
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014167359897244853,
      "loss": 0.0343,
      "step": 388
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001413828683993628,
      "loss": 0.0149,
      "step": 389
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014109171514507872,
      "loss": 0.0431,
      "step": 390
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014080014218341162,
      "loss": 0.0138,
      "step": 391
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014050815249246363,
      "loss": 0.0514,
      "step": 392
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014021574905459332,
      "loss": 0.0206,
      "step": 393
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001399229348563852,
      "loss": 0.0283,
      "step": 394
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013962971288861937,
      "loss": 0.031,
      "step": 395
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013933608614624072,
      "loss": 0.0139,
      "step": 396
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013904205762832857,
      "loss": 0.0078,
      "step": 397
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001387476303380659,
      "loss": 0.0153,
      "step": 398
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013845280728270865,
      "loss": 0.0255,
      "step": 399
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013815759147355533,
      "loss": 0.0398,
      "step": 400
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013786198592591562,
      "loss": 0.0552,
      "step": 401
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013756599365908026,
      "loss": 0.0043,
      "step": 402
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001372696176962898,
      "loss": 0.0185,
      "step": 403
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013697286106470377,
      "loss": 0.0378,
      "step": 404
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013667572679536998,
      "loss": 0.0256,
      "step": 405
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013637821792319326,
      "loss": 0.0253,
      "step": 406
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013608033748690462,
      "loss": 0.0164,
      "step": 407
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013578208852903025,
      "loss": 0.0104,
      "step": 408
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013548347409586038,
      "loss": 0.0223,
      "step": 409
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001351844972374181,
      "loss": 0.0188,
      "step": 410
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001348851610074284,
      "loss": 0.0164,
      "step": 411
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013458546846328674,
      "loss": 0.0278,
      "step": 412
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001342854226660281,
      "loss": 0.0499,
      "step": 413
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001339850266802953,
      "loss": 0.0306,
      "step": 414
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013368428357430826,
      "loss": 0.0262,
      "step": 415
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013338319641983216,
      "loss": 0.0204,
      "step": 416
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001330817682921463,
      "loss": 0.0077,
      "step": 417
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001327800022700127,
      "loss": 0.0423,
      "step": 418
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013247790143564457,
      "loss": 0.0641,
      "step": 419
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013217546887467482,
      "loss": 0.0142,
      "step": 420
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001318727076761247,
      "loss": 0.0455,
      "step": 421
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001315696209323721,
      "loss": 0.0189,
      "step": 422
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013126621173911986,
      "loss": 0.0619,
      "step": 423
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013096248319536454,
      "loss": 0.0341,
      "step": 424
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013065843840336428,
      "loss": 0.0296,
      "step": 425
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001303540804686075,
      "loss": 0.0196,
      "step": 426
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013004941249978105,
      "loss": 0.0345,
      "step": 427
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012974443760873833,
      "loss": 0.0204,
      "step": 428
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012943915891046768,
      "loss": 0.0169,
      "step": 429
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001291335795230605,
      "loss": 0.0121,
      "step": 430
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001288277025676794,
      "loss": 0.0483,
      "step": 431
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012852153116852638,
      "loss": 0.0652,
      "step": 432
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012821506845281077,
      "loss": 0.0405,
      "step": 433
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001279083175507174,
      "loss": 0.0348,
      "step": 434
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012760128159537468,
      "loss": 0.0241,
      "step": 435
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012729396372282244,
      "loss": 0.0087,
      "step": 436
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001269863670719801,
      "loss": 0.0073,
      "step": 437
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012667849478461437,
      "loss": 0.0501,
      "step": 438
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001263703500053074,
      "loss": 0.0156,
      "step": 439
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012606193588142448,
      "loss": 0.0218,
      "step": 440
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000125753255563082,
      "loss": 0.0655,
      "step": 441
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001254443122031152,
      "loss": 0.0264,
      "step": 442
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012513510895704606,
      "loss": 0.0102,
      "step": 443
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012482564898305099,
      "loss": 0.0478,
      "step": 444
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012451593544192857,
      "loss": 0.0186,
      "step": 445
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012420597149706732,
      "loss": 0.0329,
      "step": 446
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012389576031441338,
      "loss": 0.0247,
      "step": 447
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001235853050624381,
      "loss": 0.0321,
      "step": 448
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001232746089121058,
      "loss": 0.0431,
      "step": 449
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012296367503684128,
      "loss": 0.0227,
      "step": 450
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012265250661249743,
      "loss": 0.0644,
      "step": 451
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012234110681732288,
      "loss": 0.0258,
      "step": 452
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012202947883192933,
      "loss": 0.0395,
      "step": 453
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012171762583925932,
      "loss": 0.0232,
      "step": 454
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012140555102455353,
      "loss": 0.0505,
      "step": 455
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012109325757531835,
      "loss": 0.034,
      "step": 456
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012078074868129328,
      "loss": 0.0358,
      "step": 457
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012046802753441828,
      "loss": 0.0248,
      "step": 458
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012015509732880137,
      "loss": 0.0155,
      "step": 459
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011984196126068576,
      "loss": 0.0193,
      "step": 460
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011952862252841742,
      "loss": 0.0323,
      "step": 461
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011921508433241222,
      "loss": 0.0264,
      "step": 462
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011890134987512343,
      "loss": 0.0199,
      "step": 463
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011858742236100883,
      "loss": 0.0376,
      "step": 464
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011827330499649816,
      "loss": 0.0814,
      "step": 465
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011795900098996018,
      "loss": 0.0201,
      "step": 466
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011764451355167005,
      "loss": 0.0177,
      "step": 467
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011732984589377653,
      "loss": 0.0348,
      "step": 468
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011701500123026901,
      "loss": 0.0516,
      "step": 469
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001166999827769449,
      "loss": 0.031,
      "step": 470
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011638479375137663,
      "loss": 0.0268,
      "step": 471
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001160694373728789,
      "loss": 0.0255,
      "step": 472
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011575391686247566,
      "loss": 0.0185,
      "step": 473
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011543823544286737,
      "loss": 0.0331,
      "step": 474
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011512239633839792,
      "loss": 0.0226,
      "step": 475
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011480640277502186,
      "loss": 0.0352,
      "step": 476
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011449025798027131,
      "loss": 0.0391,
      "step": 477
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011417396518322312,
      "loss": 0.0134,
      "step": 478
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011385752761446575,
      "loss": 0.021,
      "step": 479
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011354094850606637,
      "loss": 0.0422,
      "step": 480
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011322423109153789,
      "loss": 0.0293,
      "step": 481
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011290737860580576,
      "loss": 0.0099,
      "step": 482
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011259039428517511,
      "loss": 0.0183,
      "step": 483
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011227328136729756,
      "loss": 0.0039,
      "step": 484
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011195604309113829,
      "loss": 0.0201,
      "step": 485
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011163868269694285,
      "loss": 0.0208,
      "step": 486
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011132120342620402,
      "loss": 0.0478,
      "step": 487
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001110036085216289,
      "loss": 0.0364,
      "step": 488
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011068590122710559,
      "loss": 0.0159,
      "step": 489
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011036808478767013,
      "loss": 0.0268,
      "step": 490
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011005016244947337,
      "loss": 0.031,
      "step": 491
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001097321374597478,
      "loss": 0.0158,
      "step": 492
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010941401306677441,
      "loss": 0.0431,
      "step": 493
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010909579251984945,
      "loss": 0.0104,
      "step": 494
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010877747906925126,
      "loss": 0.0139,
      "step": 495
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010845907596620719,
      "loss": 0.0351,
      "step": 496
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010814058646286013,
      "loss": 0.0259,
      "step": 497
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010782201381223564,
      "loss": 0.035,
      "step": 498
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010750336126820844,
      "loss": 0.0284,
      "step": 499
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010718463208546918,
      "loss": 0.0826,
      "step": 500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010686582951949154,
      "loss": 0.0266,
      "step": 501
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010654695682649849,
      "loss": 0.017,
      "step": 502
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010622801726342939,
      "loss": 0.0489,
      "step": 503
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010590901408790663,
      "loss": 0.0081,
      "step": 504
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001055899505582022,
      "loss": 0.0518,
      "step": 505
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001052708299332047,
      "loss": 0.0289,
      "step": 506
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010495165547238579,
      "loss": 0.0471,
      "step": 507
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010463243043576702,
      "loss": 0.014,
      "step": 508
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001043131580838866,
      "loss": 0.0257,
      "step": 509
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010399384167776591,
      "loss": 0.0287,
      "step": 510
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010367448447887628,
      "loss": 0.0279,
      "step": 511
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010335508974910588,
      "loss": 0.0276,
      "step": 512
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010303566075072599,
      "loss": 0.0429,
      "step": 513
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010271620074635801,
      "loss": 0.0048,
      "step": 514
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001023967129989401,
      "loss": 0.0131,
      "step": 515
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010207720077169363,
      "loss": 0.0216,
      "step": 516
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010175766732809011,
      "loss": 0.0172,
      "step": 517
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010143811593181778,
      "loss": 0.0248,
      "step": 518
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001011185498467481,
      "loss": 0.0454,
      "step": 519
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010079897233690276,
      "loss": 0.0277,
      "step": 520
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010047938666641998,
      "loss": 0.0239,
      "step": 521
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001001597960995214,
      "loss": 0.045,
      "step": 522
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.984020390047866e-05,
      "loss": 0.0124,
      "step": 523
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.952061333358003e-05,
      "loss": 0.0268,
      "step": 524
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.920102766309726e-05,
      "loss": 0.0185,
      "step": 525
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.88814501532519e-05,
      "loss": 0.0458,
      "step": 526
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.856188406818226e-05,
      "loss": 0.034,
      "step": 527
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.82423326719099e-05,
      "loss": 0.01,
      "step": 528
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.792279922830637e-05,
      "loss": 0.0604,
      "step": 529
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.760328700105991e-05,
      "loss": 0.0344,
      "step": 530
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.728379925364199e-05,
      "loss": 0.01,
      "step": 531
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.696433924927403e-05,
      "loss": 0.0141,
      "step": 532
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.664491025089411e-05,
      "loss": 0.0078,
      "step": 533
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.632551552112374e-05,
      "loss": 0.0274,
      "step": 534
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.600615832223412e-05,
      "loss": 0.0093,
      "step": 535
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.568684191611344e-05,
      "loss": 0.0437,
      "step": 536
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.536756956423299e-05,
      "loss": 0.0295,
      "step": 537
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.504834452761426e-05,
      "loss": 0.0609,
      "step": 538
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.472917006679533e-05,
      "loss": 0.0247,
      "step": 539
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.44100494417978e-05,
      "loss": 0.0186,
      "step": 540
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.40909859120934e-05,
      "loss": 0.0437,
      "step": 541
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.377198273657061e-05,
      "loss": 0.0487,
      "step": 542
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.345304317350153e-05,
      "loss": 0.0179,
      "step": 543
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.313417048050846e-05,
      "loss": 0.0122,
      "step": 544
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.281536791453084e-05,
      "loss": 0.0119,
      "step": 545
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.24966387317916e-05,
      "loss": 0.0129,
      "step": 546
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.217798618776438e-05,
      "loss": 0.0245,
      "step": 547
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.185941353713988e-05,
      "loss": 0.0244,
      "step": 548
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.154092403379286e-05,
      "loss": 0.0237,
      "step": 549
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.122252093074876e-05,
      "loss": 0.0372,
      "step": 550
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.09042074801506e-05,
      "loss": 0.0291,
      "step": 551
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.05859869332256e-05,
      "loss": 0.0111,
      "step": 552
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.026786254025219e-05,
      "loss": 0.0156,
      "step": 553
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.994983755052664e-05,
      "loss": 0.024,
      "step": 554
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.963191521232988e-05,
      "loss": 0.0206,
      "step": 555
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.931409877289444e-05,
      "loss": 0.0147,
      "step": 556
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.899639147837108e-05,
      "loss": 0.023,
      "step": 557
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.867879657379599e-05,
      "loss": 0.0323,
      "step": 558
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.836131730305718e-05,
      "loss": 0.0094,
      "step": 559
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.804395690886173e-05,
      "loss": 0.0279,
      "step": 560
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.772671863270247e-05,
      "loss": 0.0357,
      "step": 561
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.740960571482495e-05,
      "loss": 0.0418,
      "step": 562
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.709262139419425e-05,
      "loss": 0.0131,
      "step": 563
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.677576890846212e-05,
      "loss": 0.013,
      "step": 564
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.645905149393364e-05,
      "loss": 0.0106,
      "step": 565
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.614247238553427e-05,
      "loss": 0.0133,
      "step": 566
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.582603481677692e-05,
      "loss": 0.0486,
      "step": 567
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.550974201972869e-05,
      "loss": 0.0154,
      "step": 568
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.519359722497817e-05,
      "loss": 0.0118,
      "step": 569
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.48776036616021e-05,
      "loss": 0.0112,
      "step": 570
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.456176455713268e-05,
      "loss": 0.0043,
      "step": 571
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.424608313752436e-05,
      "loss": 0.0357,
      "step": 572
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.393056262712115e-05,
      "loss": 0.0189,
      "step": 573
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.361520624862338e-05,
      "loss": 0.0276,
      "step": 574
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.330001722305511e-05,
      "loss": 0.0067,
      "step": 575
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.298499876973101e-05,
      "loss": 0.0235,
      "step": 576
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.26701541062235e-05,
      "loss": 0.0619,
      "step": 577
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.235548644832996e-05,
      "loss": 0.0081,
      "step": 578
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.204099901003983e-05,
      "loss": 0.0023,
      "step": 579
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.172669500350188e-05,
      "loss": 0.0408,
      "step": 580
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.141257763899118e-05,
      "loss": 0.021,
      "step": 581
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.109865012487662e-05,
      "loss": 0.0293,
      "step": 582
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.078491566758782e-05,
      "loss": 0.0467,
      "step": 583
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.047137747158263e-05,
      "loss": 0.0175,
      "step": 584
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.015803873931425e-05,
      "loss": 0.0271,
      "step": 585
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.984490267119867e-05,
      "loss": 0.0222,
      "step": 586
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.953197246558173e-05,
      "loss": 0.0149,
      "step": 587
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.921925131870673e-05,
      "loss": 0.0121,
      "step": 588
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.890674242468166e-05,
      "loss": 0.0379,
      "step": 589
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.859444897544646e-05,
      "loss": 0.0121,
      "step": 590
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.82823741607407e-05,
      "loss": 0.0087,
      "step": 591
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.797052116807068e-05,
      "loss": 0.0289,
      "step": 592
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.765889318267717e-05,
      "loss": 0.0309,
      "step": 593
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.73474933875026e-05,
      "loss": 0.0268,
      "step": 594
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.703632496315878e-05,
      "loss": 0.0101,
      "step": 595
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.672539108789423e-05,
      "loss": 0.0077,
      "step": 596
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.641469493756195e-05,
      "loss": 0.0066,
      "step": 597
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.610423968558666e-05,
      "loss": 0.0315,
      "step": 598
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.579402850293271e-05,
      "loss": 0.0136,
      "step": 599
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.548406455807146e-05,
      "loss": 0.0316,
      "step": 600
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.517435101694902e-05,
      "loss": 0.0247,
      "step": 601
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.486489104295396e-05,
      "loss": 0.0153,
      "step": 602
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.455568779688482e-05,
      "loss": 0.0242,
      "step": 603
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.424674443691804e-05,
      "loss": 0.0384,
      "step": 604
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.393806411857554e-05,
      "loss": 0.0082,
      "step": 605
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.362964999469264e-05,
      "loss": 0.0143,
      "step": 606
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.332150521538564e-05,
      "loss": 0.0078,
      "step": 607
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.301363292801997e-05,
      "loss": 0.0141,
      "step": 608
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.270603627717758e-05,
      "loss": 0.0272,
      "step": 609
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.239871840462536e-05,
      "loss": 0.0111,
      "step": 610
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.209168244928264e-05,
      "loss": 0.0282,
      "step": 611
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.178493154718924e-05,
      "loss": 0.0166,
      "step": 612
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.147846883147363e-05,
      "loss": 0.0169,
      "step": 613
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.117229743232058e-05,
      "loss": 0.0188,
      "step": 614
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.086642047693952e-05,
      "loss": 0.0136,
      "step": 615
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.056084108953233e-05,
      "loss": 0.0425,
      "step": 616
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.02555623912617e-05,
      "loss": 0.0517,
      "step": 617
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.995058750021896e-05,
      "loss": 0.0124,
      "step": 618
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.964591953139252e-05,
      "loss": 0.0101,
      "step": 619
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.934156159663574e-05,
      "loss": 0.0473,
      "step": 620
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.903751680463549e-05,
      "loss": 0.0291,
      "step": 621
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.873378826088015e-05,
      "loss": 0.019,
      "step": 622
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.843037906762792e-05,
      "loss": 0.0197,
      "step": 623
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.812729232387532e-05,
      "loss": 0.0193,
      "step": 624
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.782453112532516e-05,
      "loss": 0.0102,
      "step": 625
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.752209856435546e-05,
      "loss": 0.0168,
      "step": 626
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.721999772998731e-05,
      "loss": 0.028,
      "step": 627
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.691823170785374e-05,
      "loss": 0.0273,
      "step": 628
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.661680358016785e-05,
      "loss": 0.0023,
      "step": 629
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.631571642569179e-05,
      "loss": 0.017,
      "step": 630
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.60149733197047e-05,
      "loss": 0.0125,
      "step": 631
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.571457733397196e-05,
      "loss": 0.0188,
      "step": 632
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.541453153671327e-05,
      "loss": 0.0136,
      "step": 633
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.51148389925716e-05,
      "loss": 0.0251,
      "step": 634
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.481550276258193e-05,
      "loss": 0.0159,
      "step": 635
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.451652590413963e-05,
      "loss": 0.009,
      "step": 636
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.421791147096976e-05,
      "loss": 0.041,
      "step": 637
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.39196625130954e-05,
      "loss": 0.0058,
      "step": 638
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.362178207680678e-05,
      "loss": 0.0086,
      "step": 639
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.332427320463003e-05,
      "loss": 0.0465,
      "step": 640
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.302713893529626e-05,
      "loss": 0.0184,
      "step": 641
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.273038230371023e-05,
      "loss": 0.018,
      "step": 642
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.243400634091978e-05,
      "loss": 0.0164,
      "step": 643
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.213801407408442e-05,
      "loss": 0.0046,
      "step": 644
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.18424085264447e-05,
      "loss": 0.0431,
      "step": 645
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.154719271729134e-05,
      "loss": 0.0119,
      "step": 646
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.125236966193412e-05,
      "loss": 0.037,
      "step": 647
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.095794237167145e-05,
      "loss": 0.0224,
      "step": 648
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.066391385375929e-05,
      "loss": 0.0208,
      "step": 649
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.037028711138066e-05,
      "loss": 0.0066,
      "step": 650
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.007706514361482e-05,
      "loss": 0.0254,
      "step": 651
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.9784250945406737e-05,
      "loss": 0.0326,
      "step": 652
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.949184750753638e-05,
      "loss": 0.0098,
      "step": 653
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.91998578165884e-05,
      "loss": 0.0166,
      "step": 654
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.890828485492129e-05,
      "loss": 0.0316,
      "step": 655
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.861713160063721e-05,
      "loss": 0.0422,
      "step": 656
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.832640102755148e-05,
      "loss": 0.004,
      "step": 657
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.8036096105162095e-05,
      "loss": 0.0094,
      "step": 658
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.7746219798619625e-05,
      "loss": 0.0436,
      "step": 659
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.7456775068696554e-05,
      "loss": 0.0243,
      "step": 660
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.7167764871757636e-05,
      "loss": 0.008,
      "step": 661
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.687919215972899e-05,
      "loss": 0.0098,
      "step": 662
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.659105988006852e-05,
      "loss": 0.0158,
      "step": 663
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6303370975735495e-05,
      "loss": 0.0705,
      "step": 664
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.601612838516066e-05,
      "loss": 0.0221,
      "step": 665
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.572933504221599e-05,
      "loss": 0.0326,
      "step": 666
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.544299387618514e-05,
      "loss": 0.0217,
      "step": 667
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.515710781173301e-05,
      "loss": 0.0207,
      "step": 668
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.487167976887627e-05,
      "loss": 0.0251,
      "step": 669
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.4586712662953365e-05,
      "loss": 0.0379,
      "step": 670
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.430220940459478e-05,
      "loss": 0.0259,
      "step": 671
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.401817289969331e-05,
      "loss": 0.039,
      "step": 672
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.373460604937424e-05,
      "loss": 0.0163,
      "step": 673
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.34515117499661e-05,
      "loss": 0.0182,
      "step": 674
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.3168892892970536e-05,
      "loss": 0.0156,
      "step": 675
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.288675236503328e-05,
      "loss": 0.0498,
      "step": 676
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.260509304791433e-05,
      "loss": 0.0253,
      "step": 677
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.232391781845875e-05,
      "loss": 0.0207,
      "step": 678
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.204322954856695e-05,
      "loss": 0.0397,
      "step": 679
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.176303110516587e-05,
      "loss": 0.0339,
      "step": 680
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.1483325350179254e-05,
      "loss": 0.0265,
      "step": 681
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.120411514049843e-05,
      "loss": 0.0323,
      "step": 682
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.092540332795359e-05,
      "loss": 0.03,
      "step": 683
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.0647192759284044e-05,
      "loss": 0.0195,
      "step": 684
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.0369486276109554e-05,
      "loss": 0.0271,
      "step": 685
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.0092286714901225e-05,
      "loss": 0.0147,
      "step": 686
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.981559690695251e-05,
      "loss": 0.0168,
      "step": 687
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.9539419678350104e-05,
      "loss": 0.0277,
      "step": 688
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.926375784994558e-05,
      "loss": 0.0092,
      "step": 689
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.898861423732594e-05,
      "loss": 0.0093,
      "step": 690
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.871399165078534e-05,
      "loss": 0.0215,
      "step": 691
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.8439892895296215e-05,
      "loss": 0.0278,
      "step": 692
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.816632077048059e-05,
      "loss": 0.0058,
      "step": 693
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.789327807058157e-05,
      "loss": 0.0296,
      "step": 694
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.7620767584434634e-05,
      "loss": 0.0323,
      "step": 695
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.73487920954395e-05,
      "loss": 0.0127,
      "step": 696
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.7077354381531244e-05,
      "loss": 0.0122,
      "step": 697
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.6806457215152287e-05,
      "loss": 0.0231,
      "step": 698
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.653610336322388e-05,
      "loss": 0.0439,
      "step": 699
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.6266295587117995e-05,
      "loss": 0.0402,
      "step": 700
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.599703664262882e-05,
      "loss": 0.018,
      "step": 701
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.5728329279945094e-05,
      "loss": 0.0261,
      "step": 702
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.5460176243621614e-05,
      "loss": 0.0226,
      "step": 703
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.519258027255121e-05,
      "loss": 0.0288,
      "step": 704
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.492554409993719e-05,
      "loss": 0.0215,
      "step": 705
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.465907045326483e-05,
      "loss": 0.0141,
      "step": 706
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.4393162054273985e-05,
      "loss": 0.0324,
      "step": 707
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.412782161893105e-05,
      "loss": 0.0056,
      "step": 708
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.386305185740136e-05,
      "loss": 0.0045,
      "step": 709
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.359885547402132e-05,
      "loss": 0.0581,
      "step": 710
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.333523516727096e-05,
      "loss": 0.008,
      "step": 711
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.3072193629746335e-05,
      "loss": 0.0091,
      "step": 712
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.280973354813197e-05,
      "loss": 0.0333,
      "step": 713
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.2547857603173445e-05,
      "loss": 0.0203,
      "step": 714
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.228656846965004e-05,
      "loss": 0.0124,
      "step": 715
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.202586881634739e-05,
      "loss": 0.0192,
      "step": 716
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.17657613060301e-05,
      "loss": 0.0082,
      "step": 717
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.150624859541496e-05,
      "loss": 0.026,
      "step": 718
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.1247333335143227e-05,
      "loss": 0.007,
      "step": 719
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.0989018169754e-05,
      "loss": 0.0198,
      "step": 720
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.0731305737657054e-05,
      "loss": 0.0128,
      "step": 721
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.04741986711059e-05,
      "loss": 0.0046,
      "step": 722
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.0217699596170754e-05,
      "loss": 0.0309,
      "step": 723
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.996181113271214e-05,
      "loss": 0.0352,
      "step": 724
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.970653589435356e-05,
      "loss": 0.0225,
      "step": 725
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.945187648845523e-05,
      "loss": 0.0239,
      "step": 726
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.919783551608729e-05,
      "loss": 0.0168,
      "step": 727
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.894441557200325e-05,
      "loss": 0.0344,
      "step": 728
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.869161924461345e-05,
      "loss": 0.0206,
      "step": 729
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.8439449115958726e-05,
      "loss": 0.0225,
      "step": 730
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.8187907761683935e-05,
      "loss": 0.0117,
      "step": 731
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.793699775101164e-05,
      "loss": 0.0151,
      "step": 732
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.7686721646715974e-05,
      "loss": 0.0145,
      "step": 733
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.743708200509639e-05,
      "loss": 0.0288,
      "step": 734
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.718808137595158e-05,
      "loss": 0.0412,
      "step": 735
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.693972230255336e-05,
      "loss": 0.0193,
      "step": 736
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.6692007321620815e-05,
      "loss": 0.0169,
      "step": 737
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.644493896329431e-05,
      "loss": 0.0315,
      "step": 738
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.619851975110953e-05,
      "loss": 0.0126,
      "step": 739
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.5952752201972094e-05,
      "loss": 0.0114,
      "step": 740
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.570763882613135e-05,
      "loss": 0.0139,
      "step": 741
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.546318212715508e-05,
      "loss": 0.0207,
      "step": 742
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.5219384601903814e-05,
      "loss": 0.0089,
      "step": 743
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.497624874050537e-05,
      "loss": 0.0016,
      "step": 744
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.473377702632924e-05,
      "loss": 0.0192,
      "step": 745
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.449197193596161e-05,
      "loss": 0.0169,
      "step": 746
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.4250835939179585e-05,
      "loss": 0.0064,
      "step": 747
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.401037149892635e-05,
      "loss": 0.0057,
      "step": 748
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.377058107128583e-05,
      "loss": 0.0175,
      "step": 749
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.353146710545765e-05,
      "loss": 0.0243,
      "step": 750
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.3293032043732076e-05,
      "loss": 0.0526,
      "step": 751
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.3055278321465146e-05,
      "loss": 0.0138,
      "step": 752
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.281820836705375e-05,
      "loss": 0.0202,
      "step": 753
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.2581824601910746e-05,
      "loss": 0.0096,
      "step": 754
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.234612944044044e-05,
      "loss": 0.0396,
      "step": 755
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.21111252900137e-05,
      "loss": 0.0085,
      "step": 756
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.1876814550943525e-05,
      "loss": 0.0288,
      "step": 757
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.164319961646043e-05,
      "loss": 0.0208,
      "step": 758
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.141028287268808e-05,
      "loss": 0.0241,
      "step": 759
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.11780666986188e-05,
      "loss": 0.0147,
      "step": 760
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.094655346608939e-05,
      "loss": 0.024,
      "step": 761
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.071574553975698e-05,
      "loss": 0.014,
      "step": 762
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0485645277074572e-05,
      "loss": 0.0076,
      "step": 763
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0256255028267245e-05,
      "loss": 0.0262,
      "step": 764
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.002757713630806e-05,
      "loss": 0.0172,
      "step": 765
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9799613936894135e-05,
      "loss": 0.0534,
      "step": 766
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.957236775842266e-05,
      "loss": 0.0041,
      "step": 767
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.934584092196745e-05,
      "loss": 0.047,
      "step": 768
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9120035741254803e-05,
      "loss": 0.0117,
      "step": 769
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8894954522640204e-05,
      "loss": 0.011,
      "step": 770
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8670599565084634e-05,
      "loss": 0.0204,
      "step": 771
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8446973160131064e-05,
      "loss": 0.0276,
      "step": 772
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8224077591881138e-05,
      "loss": 0.0126,
      "step": 773
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8001915136971758e-05,
      "loss": 0.0239,
      "step": 774
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.7780488064551923e-05,
      "loss": 0.0152,
      "step": 775
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7559798636259394e-05,
      "loss": 0.0103,
      "step": 776
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7339849106197768e-05,
      "loss": 0.0138,
      "step": 777
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.71206417209134e-05,
      "loss": 0.0406,
      "step": 778
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6902178719372405e-05,
      "loss": 0.0093,
      "step": 779
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6684462332937766e-05,
      "loss": 0.0288,
      "step": 780
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.646749478534678e-05,
      "loss": 0.0075,
      "step": 781
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6251278292687943e-05,
      "loss": 0.0086,
      "step": 782
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6035815063378664e-05,
      "loss": 0.0154,
      "step": 783
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5821107298142643e-05,
      "loss": 0.0046,
      "step": 784
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5607157189987163e-05,
      "loss": 0.0186,
      "step": 785
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.539396692418099e-05,
      "loss": 0.0171,
      "step": 786
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5181538678231864e-05,
      "loss": 0.017,
      "step": 787
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4969874621864375e-05,
      "loss": 0.0195,
      "step": 788
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4758976916997624e-05,
      "loss": 0.0113,
      "step": 789
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4548847717723454e-05,
      "loss": 0.0112,
      "step": 790
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4339489170284058e-05,
      "loss": 0.0084,
      "step": 791
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4130903413050353e-05,
      "loss": 0.0034,
      "step": 792
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.392309257650005e-05,
      "loss": 0.0118,
      "step": 793
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3716058783195872e-05,
      "loss": 0.0219,
      "step": 794
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3509804147763838e-05,
      "loss": 0.0667,
      "step": 795
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.330433077687173e-05,
      "loss": 0.0342,
      "step": 796
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.3099640769207686e-05,
      "loss": 0.0069,
      "step": 797
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.289573621545843e-05,
      "loss": 0.0115,
      "step": 798
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2692619198288257e-05,
      "loss": 0.0064,
      "step": 799
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.249029179231761e-05,
      "loss": 0.0279,
      "step": 800
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.22887560641019e-05,
      "loss": 0.0035,
      "step": 801
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.208801407211033e-05,
      "loss": 0.0185,
      "step": 802
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.188806786670513e-05,
      "loss": 0.0187,
      "step": 803
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.168891949012024e-05,
      "loss": 0.0264,
      "step": 804
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.149057097644075e-05,
      "loss": 0.012,
      "step": 805
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.129302435158198e-05,
      "loss": 0.0038,
      "step": 806
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.1096281633268843e-05,
      "loss": 0.045,
      "step": 807
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0900344831015206e-05,
      "loss": 0.0109,
      "step": 808
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.070521594610336e-05,
      "loss": 0.0376,
      "step": 809
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0510896971563663e-05,
      "loss": 0.0081,
      "step": 810
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0317389892153972e-05,
      "loss": 0.0033,
      "step": 811
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0124696684339717e-05,
      "loss": 0.0037,
      "step": 812
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.993281931627331e-05,
      "loss": 0.0241,
      "step": 813
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.974175974777437e-05,
      "loss": 0.0195,
      "step": 814
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9551519930309536e-05,
      "loss": 0.008,
      "step": 815
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.936210180697262e-05,
      "loss": 0.0544,
      "step": 816
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.917350731246462e-05,
      "loss": 0.0097,
      "step": 817
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8985738373074124e-05,
      "loss": 0.0513,
      "step": 818
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8798796906657635e-05,
      "loss": 0.0087,
      "step": 819
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8612684822619776e-05,
      "loss": 0.0157,
      "step": 820
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8427404021894013e-05,
      "loss": 0.0055,
      "step": 821
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8242956396923126e-05,
      "loss": 0.0101,
      "step": 822
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8059343831639963e-05,
      "loss": 0.012,
      "step": 823
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7876568201448006e-05,
      "loss": 0.0193,
      "step": 824
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.769463137320254e-05,
      "loss": 0.0115,
      "step": 825
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7513535205191224e-05,
      "loss": 0.0141,
      "step": 826
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7333281547115366e-05,
      "loss": 0.0134,
      "step": 827
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7153872240070945e-05,
      "loss": 0.0089,
      "step": 828
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6975309116529803e-05,
      "loss": 0.0202,
      "step": 829
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6797594000320914e-05,
      "loss": 0.0067,
      "step": 830
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.662072870661181e-05,
      "loss": 0.0069,
      "step": 831
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.644471504188999e-05,
      "loss": 0.0034,
      "step": 832
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6269554803944444e-05,
      "loss": 0.0204,
      "step": 833
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6095249781847398e-05,
      "loss": 0.0403,
      "step": 834
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.592180175593593e-05,
      "loss": 0.0138,
      "step": 835
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5749212497793865e-05,
      "loss": 0.022,
      "step": 836
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5577483770233603e-05,
      "loss": 0.019,
      "step": 837
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5406617327278205e-05,
      "loss": 0.0145,
      "step": 838
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5236614914143365e-05,
      "loss": 0.0166,
      "step": 839
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5067478267219704e-05,
      "loss": 0.0239,
      "step": 840
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4899209114054946e-05,
      "loss": 0.0155,
      "step": 841
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.473180917333633e-05,
      "loss": 0.0419,
      "step": 842
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4565280154873006e-05,
      "loss": 0.0072,
      "step": 843
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4399623759578618e-05,
      "loss": 0.0176,
      "step": 844
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4234841679453925e-05,
      "loss": 0.0216,
      "step": 845
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4070935597569401e-05,
      "loss": 0.0075,
      "step": 846
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3907907188048308e-05,
      "loss": 0.0353,
      "step": 847
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.37457581160493e-05,
      "loss": 0.015,
      "step": 848
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3584490037749608e-05,
      "loss": 0.0159,
      "step": 849
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3424104600328057e-05,
      "loss": 0.0151,
      "step": 850
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3264603441948276e-05,
      "loss": 0.0142,
      "step": 851
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3105988191741857e-05,
      "loss": 0.0171,
      "step": 852
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2948260469791928e-05,
      "loss": 0.0115,
      "step": 853
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2791421887116395e-05,
      "loss": 0.0059,
      "step": 854
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2635474045651552e-05,
      "loss": 0.0136,
      "step": 855
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2480418538235773e-05,
      "loss": 0.0073,
      "step": 856
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2326256948593206e-05,
      "loss": 0.0114,
      "step": 857
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2172990851317578e-05,
      "loss": 0.011,
      "step": 858
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.202062181185617e-05,
      "loss": 0.0299,
      "step": 859
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1869151386493748e-05,
      "loss": 0.0175,
      "step": 860
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1718581122336702e-05,
      "loss": 0.018,
      "step": 861
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1568912557297284e-05,
      "loss": 0.0304,
      "step": 862
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1420147220077848e-05,
      "loss": 0.0181,
      "step": 863
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1272286630155249e-05,
      "loss": 0.0164,
      "step": 864
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1125332297765345e-05,
      "loss": 0.0273,
      "step": 865
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0979285723887534e-05,
      "loss": 0.0129,
      "step": 866
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0834148400229483e-05,
      "loss": 0.0291,
      "step": 867
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0689921809211767e-05,
      "loss": 0.0057,
      "step": 868
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0546607423952937e-05,
      "loss": 0.0075,
      "step": 869
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0404206708254216e-05,
      "loss": 0.0413,
      "step": 870
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0262721116584795e-05,
      "loss": 0.0088,
      "step": 871
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0122152094066783e-05,
      "loss": 0.0226,
      "step": 872
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.982501076460604e-06,
      "loss": 0.075,
      "step": 873
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.843769490150146e-06,
      "loss": 0.0301,
      "step": 874
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.705958752128442e-06,
      "loss": 0.0312,
      "step": 875
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.569070269982939e-06,
      "loss": 0.0224,
      "step": 876
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.433105441881274e-06,
      "loss": 0.0182,
      "step": 877
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.298065656556999e-06,
      "loss": 0.0221,
      "step": 878
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.163952293295296e-06,
      "loss": 0.1938,
      "step": 879
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.030766721918993e-06,
      "loss": 0.0283,
      "step": 880
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.898510302774499e-06,
      "loss": 0.0062,
      "step": 881
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.767184386717985e-06,
      "loss": 0.0116,
      "step": 882
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.636790315101451e-06,
      "loss": 0.0227,
      "step": 883
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.507329419759191e-06,
      "loss": 0.0092,
      "step": 884
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.378803022994109e-06,
      "loss": 0.0065,
      "step": 885
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.251212437564193e-06,
      "loss": 0.0257,
      "step": 886
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.124558966669116e-06,
      "loss": 0.0102,
      "step": 887
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.998843903936993e-06,
      "loss": 0.0122,
      "step": 888
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.874068533411095e-06,
      "loss": 0.024,
      "step": 889
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.750234129536693e-06,
      "loss": 0.0225,
      "step": 890
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.627341957148238e-06,
      "loss": 0.0193,
      "step": 891
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.505393271456152e-06,
      "loss": 0.0164,
      "step": 892
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.384389318034257e-06,
      "loss": 0.0078,
      "step": 893
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.26433133280695e-06,
      "loss": 0.0018,
      "step": 894
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.145220542036568e-06,
      "loss": 0.0166,
      "step": 895
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.0270581623108404e-06,
      "loss": 0.0077,
      "step": 896
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.909845400530624e-06,
      "loss": 0.011,
      "step": 897
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.7935834538973235e-06,
      "loss": 0.0258,
      "step": 898
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.678273509900878e-06,
      "loss": 0.0074,
      "step": 899
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.56391674630753e-06,
      "loss": 0.0383,
      "step": 900
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.4505143311478055e-06,
      "loss": 0.0244,
      "step": 901
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.338067422704619e-06,
      "loss": 0.0199,
      "step": 902
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.2265771695013574e-06,
      "loss": 0.0094,
      "step": 903
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.116044710290325e-06,
      "loss": 0.0139,
      "step": 904
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.0064711740408616e-06,
      "loss": 0.0312,
      "step": 905
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.8978576799280425e-06,
      "loss": 0.0205,
      "step": 906
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.790205337321109e-06,
      "loss": 0.0185,
      "step": 907
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.683515245772231e-06,
      "loss": 0.0084,
      "step": 908
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.57778849500511e-06,
      "loss": 0.0188,
      "step": 909
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.473026164904116e-06,
      "loss": 0.0352,
      "step": 910
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.369229325503022e-06,
      "loss": 0.0265,
      "step": 911
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.266399036974112e-06,
      "loss": 0.0117,
      "step": 912
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.164536349617533e-06,
      "loss": 0.0057,
      "step": 913
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.063642303850302e-06,
      "loss": 0.0071,
      "step": 914
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.963717930195888e-06,
      "loss": 0.0131,
      "step": 915
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.864764249273579e-06,
      "loss": 0.005,
      "step": 916
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.766782271788117e-06,
      "loss": 0.0206,
      "step": 917
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.669772998519295e-06,
      "loss": 0.0046,
      "step": 918
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.573737420311808e-06,
      "loss": 0.0043,
      "step": 919
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.47867651806515e-06,
      "loss": 0.0234,
      "step": 920
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.384591262723492e-06,
      "loss": 0.0038,
      "step": 921
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.291482615265874e-06,
      "loss": 0.0028,
      "step": 922
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.199351526696327e-06,
      "loss": 0.0099,
      "step": 923
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.10819893803418e-06,
      "loss": 0.0202,
      "step": 924
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.018025780304413e-06,
      "loss": 0.0159,
      "step": 925
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.928832974528251e-06,
      "loss": 0.007,
      "step": 926
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.84062143171362e-06,
      "loss": 0.0128,
      "step": 927
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.7533920528459165e-06,
      "loss": 0.0077,
      "step": 928
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.667145728878829e-06,
      "loss": 0.0072,
      "step": 929
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.5818833407251895e-06,
      "loss": 0.0192,
      "step": 930
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.497605759247946e-06,
      "loss": 0.0074,
      "step": 931
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.4143138452513932e-06,
      "loss": 0.0138,
      "step": 932
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.332008449472246e-06,
      "loss": 0.0154,
      "step": 933
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.250690412571e-06,
      "loss": 0.0213,
      "step": 934
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.170360565123387e-06,
      "loss": 0.0215,
      "step": 935
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.0910197276118214e-06,
      "loss": 0.0099,
      "step": 936
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.012668710417066e-06,
      "loss": 0.0113,
      "step": 937
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.9353083138099258e-06,
      "loss": 0.0158,
      "step": 938
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.858939327943122e-06,
      "loss": 0.0182,
      "step": 939
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.7835625328431315e-06,
      "loss": 0.0181,
      "step": 940
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.709178698402337e-06,
      "loss": 0.0096,
      "step": 941
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.635788584371057e-06,
      "loss": 0.0108,
      "step": 942
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.5633929403498734e-06,
      "loss": 0.0042,
      "step": 943
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.491992505781904e-06,
      "loss": 0.0166,
      "step": 944
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.421588009945286e-06,
      "loss": 0.0063,
      "step": 945
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.3521801719457282e-06,
      "loss": 0.0296,
      "step": 946
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.2837697007091265e-06,
      "loss": 0.0165,
      "step": 947
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.216357294974425e-06,
      "loss": 0.0098,
      "step": 948
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.149943643286334e-06,
      "loss": 0.0105,
      "step": 949
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.0845294239884127e-06,
      "loss": 0.0194,
      "step": 950
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.020115305216086e-06,
      "loss": 0.0092,
      "step": 951
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9567019448898603e-06,
      "loss": 0.0195,
      "step": 952
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.894289990708531e-06,
      "loss": 0.0149,
      "step": 953
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8328800801426626e-06,
      "loss": 0.006,
      "step": 954
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7724728404279855e-06,
      "loss": 0.0073,
      "step": 955
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7130688885590773e-06,
      "loss": 0.0217,
      "step": 956
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6546688312829794e-06,
      "loss": 0.0071,
      "step": 957
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.5972732650930578e-06,
      "loss": 0.0348,
      "step": 958
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.540882776222874e-06,
      "loss": 0.0146,
      "step": 959
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4854979406402347e-06,
      "loss": 0.0108,
      "step": 960
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4311193240412746e-06,
      "loss": 0.032,
      "step": 961
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3777474818446824e-06,
      "loss": 0.008,
      "step": 962
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3253829591860389e-06,
      "loss": 0.0062,
      "step": 963
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2740262909122558e-06,
      "loss": 0.0145,
      "step": 964
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2236780015761007e-06,
      "loss": 0.0179,
      "step": 965
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.174338605430847e-06,
      "loss": 0.0173,
      "step": 966
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1260086064250108e-06,
      "loss": 0.007,
      "step": 967
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.078688498197189e-06,
      "loss": 0.0011,
      "step": 968
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0323787640710626e-06,
      "loss": 0.0227,
      "step": 969
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.870798770504563e-07,
      "loss": 0.014,
      "step": 970
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.427922998144323e-07,
      "loss": 0.0042,
      "step": 971
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.99516484712648e-07,
      "loss": 0.0122,
      "step": 972
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.572528737607055e-07,
      "loss": 0.0124,
      "step": 973
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.160018986356433e-07,
      "loss": 0.0329,
      "step": 974
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.757639806714956e-07,
      "loss": 0.0171,
      "step": 975
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.365395308550405e-07,
      "loss": 0.0182,
      "step": 976
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.983289498215806e-07,
      "loss": 0.0296,
      "step": 977
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.611326278508135e-07,
      "loss": 0.0394,
      "step": 978
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.249509448629009e-07,
      "loss": 0.0228,
      "step": 979
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.897842704145728e-07,
      "loss": 0.0162,
      "step": 980
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.556329636953295e-07,
      "loss": 0.0162,
      "step": 981
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.224973735238004e-07,
      "loss": 0.0089,
      "step": 982
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.903778383441581e-07,
      "loss": 0.0135,
      "step": 983
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.592746862226882e-07,
      "loss": 0.0093,
      "step": 984
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.291882348444132e-07,
      "loss": 0.0047,
      "step": 985
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.0011879150986256e-07,
      "loss": 0.011,
      "step": 986
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.7206665313191946e-07,
      "loss": 0.0318,
      "step": 987
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.4503210623282323e-07,
      "loss": 0.0067,
      "step": 988
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.1901542694119377e-07,
      "loss": 0.0038,
      "step": 989
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.9401688098924517e-07,
      "loss": 0.012,
      "step": 990
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.700367237100543e-07,
      "loss": 0.0427,
      "step": 991
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.4707520003497406e-07,
      "loss": 0.0197,
      "step": 992
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.2513254449110234e-07,
      "loss": 0.0101,
      "step": 993
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.0420898119891675e-07,
      "loss": 0.0124,
      "step": 994
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.843047238699658e-07,
      "loss": 0.0234,
      "step": 995
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.6541997580468148e-07,
      "loss": 0.0118,
      "step": 996
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.4755492989031449e-07,
      "loss": 0.0264,
      "step": 997
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.307097685989911e-07,
      "loss": 0.0163,
      "step": 998
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.1488466398577036e-07,
      "loss": 0.0303,
      "step": 999
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0007977768697885e-07,
      "loss": 0.0177,
      "step": 1000
    },
    {
      "epoch": 0.99,
      "learning_rate": 8.629526091848972e-08,
      "loss": 0.0134,
      "step": 1001
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.353125447423504e-08,
      "loss": 0.0136,
      "step": 1002
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.178788872470698e-08,
      "loss": 0.0286,
      "step": 1003
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.106528361568108e-08,
      "loss": 0.0097,
      "step": 1004
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.1363548666961684e-08,
      "loss": 0.0107,
      "step": 1005
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.26827829712606e-08,
      "loss": 0.0164,
      "step": 1006
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.5023075193209012e-08,
      "loss": 0.0271,
      "step": 1007
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.8384503568413813e-08,
      "loss": 0.0082,
      "step": 1008
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.2767135902713723e-08,
      "loss": 0.0124,
      "step": 1009
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.171029571435452e-09,
      "loss": 0.0298,
      "step": 1010
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.596231518827487e-09,
      "loss": 0.0151,
      "step": 1011
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.0427782575715983e-09,
      "loss": 0.0041,
      "step": 1012
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.10695868449762e-10,
      "loss": 0.026,
      "step": 1013
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.0089,
      "step": 1014
    },
    {
      "epoch": 1.0,
      "step": 1014,
      "total_flos": 55825951334400.0,
      "train_loss": 0.054662292419071265,
      "train_runtime": 7573.6964,
      "train_samples_per_second": 2.141,
      "train_steps_per_second": 0.134
    }
  ],
  "max_steps": 1014,
  "num_train_epochs": 1,
  "total_flos": 55825951334400.0,
  "trial_name": null,
  "trial_params": null
}