{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8299434348297028,
  "eval_steps": 500,
  "global_step": 950,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6869,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.8396,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 0.7489,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7252,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 0.6548,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-05,
      "loss": 0.8022,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.6524,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.6981,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6e-05,
      "loss": 0.7488,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 0.6368,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6891,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-05,
      "loss": 0.7968,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.6912,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.8452,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-05,
      "loss": 0.6989,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.6685,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.5469,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.2e-05,
      "loss": 0.7915,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.6e-05,
      "loss": 0.7744,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 0.6804,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.4e-05,
      "loss": 0.7796,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.706,
      "step": 22
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.6798,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.6e-05,
      "loss": 0.6333,
      "step": 24
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 0.6012,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.52,
      "step": 26
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.6583,
      "step": 27
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.7354,
      "step": 28
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000116,
      "loss": 0.6296,
      "step": 29
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012,
      "loss": 0.6352,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000124,
      "loss": 0.6007,
      "step": 31
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.5659,
      "step": 32
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000132,
      "loss": 0.5138,
      "step": 33
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.6639,
      "step": 34
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014,
      "loss": 0.5934,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000144,
      "loss": 0.5233,
      "step": 36
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000148,
      "loss": 0.5307,
      "step": 37
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000152,
      "loss": 0.5928,
      "step": 38
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.5908,
      "step": 39
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00016,
      "loss": 0.6366,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000164,
      "loss": 0.5972,
      "step": 41
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000168,
      "loss": 0.4825,
      "step": 42
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000172,
      "loss": 0.6783,
      "step": 43
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.6082,
      "step": 44
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018,
      "loss": 0.7633,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.5988,
      "step": 46
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000188,
      "loss": 0.6658,
      "step": 47
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000192,
      "loss": 0.5945,
      "step": 48
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000196,
      "loss": 0.5984,
      "step": 49
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6778,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00020400000000000003,
      "loss": 0.6057,
      "step": 51
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00020800000000000001,
      "loss": 0.601,
      "step": 52
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00021200000000000003,
      "loss": 0.5566,
      "step": 53
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00021600000000000002,
      "loss": 0.5911,
      "step": 54
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00022000000000000003,
      "loss": 0.7636,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00022400000000000002,
      "loss": 0.5537,
      "step": 56
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00022799999999999999,
      "loss": 0.6037,
      "step": 57
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000232,
      "loss": 0.6474,
      "step": 58
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000236,
      "loss": 0.6483,
      "step": 59
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00024,
      "loss": 0.5021,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000244,
      "loss": 0.5347,
      "step": 61
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000248,
      "loss": 0.5791,
      "step": 62
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000252,
      "loss": 0.5407,
      "step": 63
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00025600000000000004,
      "loss": 0.5298,
      "step": 64
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00026000000000000003,
      "loss": 0.5685,
      "step": 65
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000264,
      "loss": 0.5108,
      "step": 66
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000268,
      "loss": 0.526,
      "step": 67
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00027200000000000005,
      "loss": 0.6843,
      "step": 68
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000276,
      "loss": 0.6608,
      "step": 69
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00028,
      "loss": 0.5866,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000284,
      "loss": 0.6422,
      "step": 71
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000288,
      "loss": 0.449,
      "step": 72
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000292,
      "loss": 0.5319,
      "step": 73
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000296,
      "loss": 0.5977,
      "step": 74
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00030000000000000003,
      "loss": 0.5805,
      "step": 75
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000304,
      "loss": 0.5209,
      "step": 76
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000308,
      "loss": 0.6098,
      "step": 77
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00031200000000000005,
      "loss": 0.4665,
      "step": 78
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00031600000000000004,
      "loss": 0.6882,
      "step": 79
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00032,
      "loss": 0.5427,
      "step": 80
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000324,
      "loss": 0.5345,
      "step": 81
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000328,
      "loss": 0.663,
      "step": 82
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000332,
      "loss": 0.5393,
      "step": 83
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000336,
      "loss": 0.5711,
      "step": 84
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00034,
      "loss": 0.5261,
      "step": 85
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000344,
      "loss": 0.5775,
      "step": 86
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000348,
      "loss": 0.6329,
      "step": 87
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00035200000000000005,
      "loss": 0.4425,
      "step": 88
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00035600000000000003,
      "loss": 0.6837,
      "step": 89
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00036,
      "loss": 0.615,
      "step": 90
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000364,
      "loss": 0.5615,
      "step": 91
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00036800000000000005,
      "loss": 0.5434,
      "step": 92
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00037200000000000004,
      "loss": 0.5864,
      "step": 93
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000376,
      "loss": 0.5583,
      "step": 94
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00038,
      "loss": 0.5299,
      "step": 95
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000384,
      "loss": 0.532,
      "step": 96
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000388,
      "loss": 0.5227,
      "step": 97
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000392,
      "loss": 0.5275,
      "step": 98
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00039600000000000003,
      "loss": 0.4541,
      "step": 99
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0004,
      "loss": 0.6485,
      "step": 100
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003999995350775973,
      "loss": 0.5438,
      "step": 101
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00039999814031255063,
      "loss": 0.5997,
      "step": 102
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00039999581571134455,
      "loss": 0.5322,
      "step": 103
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003999925612847867,
      "loss": 0.484,
      "step": 104
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00039998837704800766,
      "loss": 0.5961,
      "step": 105
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00039998326302046085,
      "loss": 0.7405,
      "step": 106
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00039997721922592255,
      "loss": 0.5802,
      "step": 107
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00039997024569249167,
      "loss": 0.769,
      "step": 108
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003999623424525898,
      "loss": 0.5598,
      "step": 109
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003999535095429608,
      "loss": 0.6143,
      "step": 110
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00039994374700467095,
      "loss": 0.5766,
      "step": 111
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00039993305488310836,
      "loss": 0.7695,
      "step": 112
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003999214332279831,
      "loss": 0.7153,
      "step": 113
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003999088820933269,
      "loss": 0.5835,
      "step": 114
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00039989540153749286,
      "loss": 0.6634,
      "step": 115
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000399880991623155,
      "loss": 0.6069,
      "step": 116
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003998656524173082,
      "loss": 0.7224,
      "step": 117
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000399849383991268,
      "loss": 0.5884,
      "step": 118
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003998321864206699,
      "loss": 0.5122,
      "step": 119
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00039981405978546924,
      "loss": 0.6453,
      "step": 120
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003997950041699408,
      "loss": 0.4665,
      "step": 121
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003997750196626785,
      "loss": 0.5428,
      "step": 122
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00039975410635659464,
      "loss": 0.4365,
      "step": 123
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00039973226434891995,
      "loss": 0.5978,
      "step": 124
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00039970949374120286,
      "loss": 0.7729,
      "step": 125
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000399685794639309,
      "loss": 0.6212,
      "step": 126
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00039966116715342066,
      "loss": 0.5426,
      "step": 127
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00039963561139803676,
      "loss": 0.5782,
      "step": 128
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003996091274919716,
      "loss": 0.6701,
      "step": 129
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003995817155583548,
      "loss": 0.6314,
      "step": 130
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003995533757246307,
      "loss": 0.6662,
      "step": 131
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003995241081225573,
      "loss": 0.5192,
      "step": 132
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003994939128882065,
      "loss": 0.5591,
      "step": 133
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003994627901619625,
      "loss": 0.5809,
      "step": 134
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003994307400885219,
      "loss": 0.4871,
      "step": 135
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003993977628168928,
      "loss": 0.6666,
      "step": 136
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003993638585003938,
      "loss": 0.6469,
      "step": 137
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00039932902729665357,
      "loss": 0.5727,
      "step": 138
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00039929326936761036,
      "loss": 0.6715,
      "step": 139
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00039925658487951067,
      "loss": 0.5686,
      "step": 140
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00039921897400290894,
      "loss": 0.501,
      "step": 141
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00039918043691266665,
      "loss": 0.5795,
      "step": 142
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039914097378795124,
      "loss": 0.6287,
      "step": 143
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039910058481223564,
      "loss": 0.7016,
      "step": 144
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039905927017329726,
      "loss": 0.6232,
      "step": 145
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039901703006321715,
      "loss": 0.5291,
      "step": 146
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039897386467837903,
      "loss": 0.5297,
      "step": 147
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039892977421946844,
      "loss": 0.5784,
      "step": 148
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003988847588914718,
      "loss": 0.5714,
      "step": 149
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003988388189036754,
      "loss": 0.5044,
      "step": 150
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003987919544696646,
      "loss": 0.8246,
      "step": 151
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003987441658073226,
      "loss": 0.5048,
      "step": 152
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003986954531388297,
      "loss": 0.5433,
      "step": 153
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00039864581669066186,
      "loss": 0.5251,
      "step": 154
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003985952566935902,
      "loss": 0.5708,
      "step": 155
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00039854377338267936,
      "loss": 0.6276,
      "step": 156
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00039849136699728684,
      "loss": 0.4915,
      "step": 157
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003984380377810617,
      "loss": 0.6389,
      "step": 158
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00039838378598194325,
      "loss": 0.6067,
      "step": 159
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00039832861185216045,
      "loss": 0.6136,
      "step": 160
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003982725156482301,
      "loss": 0.5597,
      "step": 161
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000398215497630956,
      "loss": 0.5957,
      "step": 162
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003981575580654278,
      "loss": 0.5853,
      "step": 163
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003980986972210194,
      "loss": 0.5462,
      "step": 164
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003980389153713881,
      "loss": 0.5302,
      "step": 165
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00039797821279447307,
      "loss": 0.5395,
      "step": 166
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00039791658977249425,
      "loss": 0.7004,
      "step": 167
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00039785404659195084,
      "loss": 0.5622,
      "step": 168
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00039779058354362013,
      "loss": 0.5759,
      "step": 169
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000397726200922556,
      "loss": 0.6184,
      "step": 170
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003976608990280877,
      "loss": 0.5488,
      "step": 171
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003975946781638183,
      "loss": 0.6162,
      "step": 172
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003975275386376236,
      "loss": 0.558,
      "step": 173
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003974594807616502,
      "loss": 0.519,
      "step": 174
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003973905048523144,
      "loss": 0.6195,
      "step": 175
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00039732061123030064,
      "loss": 0.5991,
      "step": 176
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003972498002205601,
      "loss": 0.5428,
      "step": 177
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00039717807215230896,
      "loss": 0.5323,
      "step": 178
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00039710542735902705,
      "loss": 0.5307,
      "step": 179
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003970318661784564,
      "loss": 0.5783,
      "step": 180
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003969573889525993,
      "loss": 0.5924,
      "step": 181
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00039688199602771714,
      "loss": 0.5902,
      "step": 182
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00039680568775432855,
      "loss": 0.6291,
      "step": 183
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003967284644872077,
      "loss": 0.5942,
      "step": 184
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003966503265853829,
      "loss": 0.4878,
      "step": 185
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003965712744121347,
      "loss": 0.6487,
      "step": 186
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003964913083349945,
      "loss": 0.6111,
      "step": 187
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00039641042872574233,
      "loss": 0.6072,
      "step": 188
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00039632863596040575,
      "loss": 0.716,
      "step": 189
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00039624593041925763,
      "loss": 0.6178,
      "step": 190
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003961623124868145,
      "loss": 0.6323,
      "step": 191
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00039607778255183485,
      "loss": 0.5821,
      "step": 192
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003959923410073174,
      "loss": 0.6738,
      "step": 193
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003959059882504989,
      "loss": 0.6203,
      "step": 194
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00039581872468285277,
      "loss": 0.632,
      "step": 195
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003957305507100868,
      "loss": 0.5857,
      "step": 196
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00039564146674214164,
      "loss": 0.6311,
      "step": 197
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003955514731931885,
      "loss": 0.5889,
      "step": 198
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00039546057048162763,
      "loss": 0.5201,
      "step": 199
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039536875903008607,
      "loss": 0.5581,
      "step": 200
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039527603926541586,
      "loss": 0.5104,
      "step": 201
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039518241161869193,
      "loss": 0.5978,
      "step": 202
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039508787652521013,
      "loss": 0.6244,
      "step": 203
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039499243442448536,
      "loss": 0.589,
      "step": 204
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003948960857602493,
      "loss": 0.575,
      "step": 205
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003947988309804485,
      "loss": 0.5494,
      "step": 206
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003947006705372422,
      "loss": 0.4895,
      "step": 207
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00039460160488700036,
      "loss": 0.5479,
      "step": 208
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00039450163449030124,
      "loss": 0.5893,
      "step": 209
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003944007598119297,
      "loss": 0.5451,
      "step": 210
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003942989813208747,
      "loss": 0.5582,
      "step": 211
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003941962994903273,
      "loss": 0.5121,
      "step": 212
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00039409271479767826,
      "loss": 0.6324,
      "step": 213
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000393988227724516,
      "loss": 0.6118,
      "step": 214
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003938828387566244,
      "loss": 0.6303,
      "step": 215
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003937765483839804,
      "loss": 0.7705,
      "step": 216
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003936693571007517,
      "loss": 0.6224,
      "step": 217
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003935612654052946,
      "loss": 0.5664,
      "step": 218
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00039345227380015163,
      "loss": 0.66,
      "step": 219
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00039334238279204906,
      "loss": 0.5582,
      "step": 220
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00039323159289189505,
      "loss": 0.6087,
      "step": 221
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003931199046147764,
      "loss": 0.5566,
      "step": 222
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00039300731847995716,
      "loss": 0.5775,
      "step": 223
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00039289383501087534,
      "loss": 0.5081,
      "step": 224
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00039277945473514104,
      "loss": 0.5218,
      "step": 225
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003926641781845338,
      "loss": 0.6655,
      "step": 226
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003925480058950002,
      "loss": 0.5735,
      "step": 227
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00039243093840665114,
      "loss": 0.6609,
      "step": 228
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003923129762637596,
      "loss": 0.7323,
      "step": 229
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000392194120014758,
      "loss": 0.5703,
      "step": 230
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00039207437021223583,
      "loss": 0.6545,
      "step": 231
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003919537274129366,
      "loss": 0.521,
      "step": 232
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039183219217775564,
      "loss": 0.5257,
      "step": 233
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003917097650717377,
      "loss": 0.5487,
      "step": 234
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039158644666407365,
      "loss": 0.4861,
      "step": 235
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039146223752809845,
      "loss": 0.4928,
      "step": 236
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003913371382412883,
      "loss": 0.5253,
      "step": 237
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00039121114938525756,
      "loss": 0.6155,
      "step": 238
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00039108427154575684,
      "loss": 0.55,
      "step": 239
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00039095650531266967,
      "loss": 0.6617,
      "step": 240
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00039082785128000976,
      "loss": 0.5198,
      "step": 241
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00039069831004591866,
      "loss": 0.5302,
      "step": 242
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003905678822126625,
      "loss": 0.5347,
      "step": 243
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00039043656838662946,
      "loss": 0.531,
      "step": 244
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00039030436917832697,
      "loss": 0.4884,
      "step": 245
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00039017128520237883,
      "loss": 0.6027,
      "step": 246
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003900373170775222,
      "loss": 0.5537,
      "step": 247
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00038990246542660494,
      "loss": 0.5753,
      "step": 248
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00038976673087658256,
      "loss": 0.5059,
      "step": 249
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00038963011405851537,
      "loss": 0.5118,
      "step": 250
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00038949261560756565,
      "loss": 0.5645,
      "step": 251
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003893542361629944,
      "loss": 0.5623,
      "step": 252
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00038921497636815866,
      "loss": 0.5216,
      "step": 253
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003890748368705085,
      "loss": 0.4501,
      "step": 254
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003889338183215838,
      "loss": 0.48,
      "step": 255
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00038879192137701135,
      "loss": 0.5218,
      "step": 256
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003886491466965018,
      "loss": 0.5858,
      "step": 257
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038850549494384685,
      "loss": 0.6124,
      "step": 258
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038836096678691536,
      "loss": 0.4645,
      "step": 259
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038821556289765136,
      "loss": 0.474,
      "step": 260
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038806928395207003,
      "loss": 0.4364,
      "step": 261
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038792213063025484,
      "loss": 0.5821,
      "step": 262
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003877741036163547,
      "loss": 0.5393,
      "step": 263
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003876252035985804,
      "loss": 0.5373,
      "step": 264
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003874754312692013,
      "loss": 0.6021,
      "step": 265
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003873247873245426,
      "loss": 0.4549,
      "step": 266
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003871732724649817,
      "loss": 0.5994,
      "step": 267
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003870208873949453,
      "loss": 0.4764,
      "step": 268
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00038686763282290556,
      "loss": 0.4311,
      "step": 269
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003867135094613774,
      "loss": 0.5462,
      "step": 270
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003865585180269148,
      "loss": 0.5006,
      "step": 271
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003864026592401076,
      "loss": 0.5347,
      "step": 272
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00038624593382557835,
      "loss": 0.5242,
      "step": 273
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00038608834251197856,
      "loss": 0.5005,
      "step": 274
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00038592988603198554,
      "loss": 0.5436,
      "step": 275
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000385770565122299,
      "loss": 0.4658,
      "step": 276
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003856103805236375,
      "loss": 0.5273,
      "step": 277
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038544933298073516,
      "loss": 0.436,
      "step": 278
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038528742324233804,
      "loss": 0.4785,
      "step": 279
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038512465206120086,
      "loss": 0.5366,
      "step": 280
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038496102019408324,
      "loss": 0.4448,
      "step": 281
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038479652840174637,
      "loss": 0.5132,
      "step": 282
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038463117744894955,
      "loss": 0.7918,
      "step": 283
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00038446496810444627,
      "loss": 0.5309,
      "step": 284
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00038429790114098114,
      "loss": 0.5316,
      "step": 285
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00038412997733528576,
      "loss": 0.4611,
      "step": 286
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00038396119746807563,
      "loss": 0.4609,
      "step": 287
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00038379156232404613,
      "loss": 0.5821,
      "step": 288
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003836210726918691,
      "loss": 0.5883,
      "step": 289
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003834497293641889,
      "loss": 0.5012,
      "step": 290
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00038327753313761913,
      "loss": 0.4457,
      "step": 291
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00038310448481273867,
      "loss": 0.4851,
      "step": 292
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00038293058519408787,
      "loss": 0.5622,
      "step": 293
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00038275583509016507,
      "loss": 0.5703,
      "step": 294
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00038258023531342265,
      "loss": 0.5718,
      "step": 295
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003824037866802632,
      "loss": 0.5183,
      "step": 296
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00038222649001103614,
      "loss": 0.5085,
      "step": 297
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00038204834613003323,
      "loss": 0.5388,
      "step": 298
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00038186935586548537,
      "loss": 0.5425,
      "step": 299
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003816895200495584,
      "loss": 0.447,
      "step": 300
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003815088395183493,
      "loss": 0.5541,
      "step": 301
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00038132731511188227,
      "loss": 0.5518,
      "step": 302
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000381144947674105,
      "loss": 0.5074,
      "step": 303
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003809617380528847,
      "loss": 0.5134,
      "step": 304
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003807776871000037,
      "loss": 0.4599,
      "step": 305
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003805927956711562,
      "loss": 0.5838,
      "step": 306
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00038040706462594395,
      "loss": 0.5216,
      "step": 307
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00038022049482787216,
      "loss": 0.5323,
      "step": 308
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003800330871443456,
      "loss": 0.5681,
      "step": 309
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00037984484244666446,
      "loss": 0.4172,
      "step": 310
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003796557616100207,
      "loss": 0.4958,
      "step": 311
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003794658455134934,
      "loss": 0.662,
      "step": 312
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003792750950400451,
      "loss": 0.5832,
      "step": 313
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003790835110765174,
      "loss": 0.4271,
      "step": 314
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003788910945136271,
      "loss": 0.4842,
      "step": 315
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00037869784624596186,
      "loss": 0.4656,
      "step": 316
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00037850376717197626,
      "loss": 0.4981,
      "step": 317
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00037830885819398733,
      "loss": 0.5162,
      "step": 318
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00037811312021817067,
      "loss": 0.652,
      "step": 319
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003779165541545558,
      "loss": 0.5104,
      "step": 320
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003777191609170225,
      "loss": 0.4971,
      "step": 321
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003775209414232962,
      "loss": 0.4871,
      "step": 322
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003773218965949436,
      "loss": 0.5226,
      "step": 323
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00037712202735736884,
      "loss": 0.4823,
      "step": 324
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003769213346398087,
      "loss": 0.497,
      "step": 325
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003767198193753286,
      "loss": 0.5976,
      "step": 326
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003765174825008181,
      "loss": 0.4532,
      "step": 327
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003763143249569868,
      "loss": 0.5236,
      "step": 328
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00037611034768835947,
      "loss": 0.6513,
      "step": 329
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00037590555164327224,
      "loss": 0.5686,
      "step": 330
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00037569993777386774,
      "loss": 0.456,
      "step": 331
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003754935070360909,
      "loss": 0.5181,
      "step": 332
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003752862603896846,
      "loss": 0.4765,
      "step": 333
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00037507819879818477,
      "loss": 0.5363,
      "step": 334
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00037486932322891646,
      "loss": 0.4584,
      "step": 335
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00037465963465298886,
      "loss": 0.5428,
      "step": 336
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003744491340452913,
      "loss": 0.3927,
      "step": 337
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003742378223844882,
      "loss": 0.5478,
      "step": 338
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003740257006530147,
      "loss": 0.469,
      "step": 339
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00037381276983707246,
      "loss": 0.5169,
      "step": 340
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00037359903092662434,
      "loss": 0.4797,
      "step": 341
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00037338448491539054,
      "loss": 0.5315,
      "step": 342
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00037316913280084353,
      "loss": 0.4422,
      "step": 343
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003729529755842035,
      "loss": 0.4426,
      "step": 344
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003727360142704337,
      "loss": 0.4718,
      "step": 345
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003725182498682361,
      "loss": 0.5585,
      "step": 346
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003722996833900459,
      "loss": 0.4775,
      "step": 347
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003720803158520279,
      "loss": 0.6014,
      "step": 348
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00037186014827407076,
      "loss": 0.5117,
      "step": 349
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003716391816797829,
      "loss": 0.5404,
      "step": 350
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003714174170964876,
      "loss": 0.527,
      "step": 351
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00037119485555521796,
      "loss": 0.4555,
      "step": 352
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00037097149809071255,
      "loss": 0.5372,
      "step": 353
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00037074734574141016,
      "loss": 0.5377,
      "step": 354
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003705223995494454,
      "loss": 0.4925,
      "step": 355
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00037029666056064345,
      "loss": 0.482,
      "step": 356
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00037007012982451546,
      "loss": 0.5235,
      "step": 357
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00036984280839425356,
      "loss": 0.4957,
      "step": 358
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000369614697326726,
      "loss": 0.5379,
      "step": 359
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003693857976824721,
      "loss": 0.4653,
      "step": 360
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00036915611052569785,
      "loss": 0.469,
      "step": 361
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003689256369242702,
      "loss": 0.5618,
      "step": 362
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003686943779497124,
      "loss": 0.4459,
      "step": 363
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003684623346771995,
      "loss": 0.5606,
      "step": 364
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003682295081855524,
      "loss": 0.4368,
      "step": 365
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00036799589955723375,
      "loss": 0.4168,
      "step": 366
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00036776150987834243,
      "loss": 0.4664,
      "step": 367
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00036752634023860846,
      "loss": 0.4737,
      "step": 368
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003672903917313883,
      "loss": 0.4247,
      "step": 369
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00036705366545365935,
      "loss": 0.5677,
      "step": 370
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00036681616250601505,
      "loss": 0.5441,
      "step": 371
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003665778839926599,
      "loss": 0.6247,
      "step": 372
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00036633883102140405,
      "loss": 0.5217,
      "step": 373
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003660990047036584,
      "loss": 0.4651,
      "step": 374
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003658584061544291,
      "loss": 0.4648,
      "step": 375
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003656170364923128,
      "loss": 0.6048,
      "step": 376
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036537489683949114,
      "loss": 0.4515,
      "step": 377
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003651319883217255,
      "loss": 0.5096,
      "step": 378
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036488831206835207,
      "loss": 0.4231,
      "step": 379
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036464386921227637,
      "loss": 0.4903,
      "step": 380
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036439866088996796,
      "loss": 0.5131,
      "step": 381
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003641526882414553,
      "loss": 0.5986,
      "step": 382
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003639059524103203,
      "loss": 0.6,
      "step": 383
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003636584545436931,
      "loss": 0.5216,
      "step": 384
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003634101957922468,
      "loss": 0.5144,
      "step": 385
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00036316117731019184,
      "loss": 0.4963,
      "step": 386
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003629114002552711,
      "loss": 0.5657,
      "step": 387
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00036266086578875384,
      "loss": 0.5028,
      "step": 388
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003624095750754311,
      "loss": 0.573,
      "step": 389
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00036215752928360967,
      "loss": 0.5199,
      "step": 390
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003619047295851068,
      "loss": 0.656,
      "step": 391
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00036165117715524506,
      "loss": 0.5129,
      "step": 392
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00036139687317284647,
      "loss": 0.3945,
      "step": 393
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003611418188202271,
      "loss": 0.5318,
      "step": 394
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00036088601528319196,
      "loss": 0.5344,
      "step": 395
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00036062946375102885,
      "loss": 0.5407,
      "step": 396
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003603721654165034,
      "loss": 0.5364,
      "step": 397
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00036011412147585306,
      "loss": 0.5407,
      "step": 398
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003598553331287821,
      "loss": 0.5999,
      "step": 399
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003595958015784555,
      "loss": 0.624,
      "step": 400
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00035933552803149354,
      "loss": 0.5351,
      "step": 401
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003590745136979662,
      "loss": 0.5196,
      "step": 402
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00035881275979138765,
      "loss": 0.5447,
      "step": 403
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003585502675287104,
      "loss": 0.4908,
      "step": 404
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00035828703813031986,
      "loss": 0.5172,
      "step": 405
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00035802307282002834,
      "loss": 0.5923,
      "step": 406
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003577583728250699,
      "loss": 0.568,
      "step": 407
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00035749293937609395,
      "loss": 0.4618,
      "step": 408
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003572267737071601,
      "loss": 0.5351,
      "step": 409
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003569598770557322,
      "loss": 0.5285,
      "step": 410
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00035669225066267256,
      "loss": 0.4571,
      "step": 411
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00035642389577223625,
      "loss": 0.4214,
      "step": 412
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003561548136320653,
      "loss": 0.5393,
      "step": 413
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003558850054931828,
      "loss": 0.549,
      "step": 414
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00035561447260998714,
      "loss": 0.4824,
      "step": 415
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00035534321624024656,
      "loss": 0.6244,
      "step": 416
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00035507123764509245,
      "loss": 0.5436,
      "step": 417
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003547985380890144,
      "loss": 0.5198,
      "step": 418
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00035452511883985366,
      "loss": 0.5979,
      "step": 419
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00035425098116879754,
      "loss": 0.4158,
      "step": 420
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00035397612635037356,
      "loss": 0.5125,
      "step": 421
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00035370055566244334,
      "loss": 0.4699,
      "step": 422
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003534242703861966,
      "loss": 0.5553,
      "step": 423
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00035314727180614573,
      "loss": 0.5969,
      "step": 424
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00035286956121011897,
      "loss": 0.456,
      "step": 425
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003525911398892552,
      "loss": 0.5195,
      "step": 426
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003523120091379975,
      "loss": 0.5187,
      "step": 427
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00035203217025408726,
      "loss": 0.5443,
      "step": 428
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003517516245385582,
      "loss": 0.4476,
      "step": 429
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003514703732957301,
      "loss": 0.5757,
      "step": 430
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00035118841783320304,
      "loss": 0.5129,
      "step": 431
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00035090575946185114,
      "loss": 0.6354,
      "step": 432
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00035062239949581645,
      "loss": 0.4065,
      "step": 433
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000350338339252503,
      "loss": 0.5472,
      "step": 434
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00035005358005257045,
      "loss": 0.5424,
      "step": 435
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00034976812321992816,
      "loss": 0.6127,
      "step": 436
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00034948197008172877,
      "loss": 0.63,
      "step": 437
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003491951219683625,
      "loss": 0.413,
      "step": 438
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034890758021345034,
      "loss": 0.5435,
      "step": 439
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034861934615383844,
      "loss": 0.5433,
      "step": 440
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034833042112959153,
      "loss": 0.4763,
      "step": 441
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034804080648398667,
      "loss": 0.5727,
      "step": 442
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034775050356350727,
      "loss": 0.5392,
      "step": 443
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034745951371783666,
      "loss": 0.4981,
      "step": 444
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003471678382998518,
      "loss": 0.5516,
      "step": 445
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00034687547866561703,
      "loss": 0.4965,
      "step": 446
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003465824361743779,
      "loss": 0.4982,
      "step": 447
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003462887121885544,
      "loss": 0.5619,
      "step": 448
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003459943080737353,
      "loss": 0.5273,
      "step": 449
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00034569922519867133,
      "loss": 0.517,
      "step": 450
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00034540346493526876,
      "loss": 0.4874,
      "step": 451
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003451070286585833,
      "loss": 0.5966,
      "step": 452
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003448099177468137,
      "loss": 0.4487,
      "step": 453
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003445121335812951,
      "loss": 0.5091,
      "step": 454
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003442136775464929,
      "loss": 0.407,
      "step": 455
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003439145510299958,
      "loss": 0.6327,
      "step": 456
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00034361475542251025,
      "loss": 0.4217,
      "step": 457
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003433142921178531,
      "loss": 0.6102,
      "step": 458
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003430131625129456,
      "loss": 0.5556,
      "step": 459
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00034271136800780673,
      "loss": 0.4986,
      "step": 460
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003424089100055467,
      "loss": 0.5406,
      "step": 461
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00034210578991236056,
      "loss": 0.5881,
      "step": 462
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00034180200913752157,
      "loss": 0.4869,
      "step": 463
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00034149756909337454,
      "loss": 0.5626,
      "step": 464
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003411924711953295,
      "loss": 0.564,
      "step": 465
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00034088671686185486,
      "loss": 0.6272,
      "step": 466
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003405803075144711,
      "loss": 0.4643,
      "step": 467
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003402732445777438,
      "loss": 0.5435,
      "step": 468
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00033996552947927744,
      "loss": 0.5844,
      "step": 469
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003396571636497084,
      "loss": 0.5362,
      "step": 470
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00033934814852269865,
      "loss": 0.5607,
      "step": 471
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003390384855349285,
      "loss": 0.4836,
      "step": 472
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00033872817612609065,
      "loss": 0.6555,
      "step": 473
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00033841722173888315,
      "loss": 0.4784,
      "step": 474
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00033810562381900253,
      "loss": 0.5583,
      "step": 475
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00033779338381513736,
      "loss": 0.4679,
      "step": 476
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003374805031789613,
      "loss": 0.5325,
      "step": 477
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00033716698336512654,
      "loss": 0.6601,
      "step": 478
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.000336852825831257,
      "loss": 0.4838,
      "step": 479
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003365380320379414,
      "loss": 0.5588,
      "step": 480
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00033622260344872665,
      "loss": 0.4596,
      "step": 481
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003359065415301108,
      "loss": 0.5228,
      "step": 482
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00033558984775153663,
      "loss": 0.5316,
      "step": 483
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00033527252358538437,
      "loss": 0.4761,
      "step": 484
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003349545705069653,
      "loss": 0.5254,
      "step": 485
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003346359899945144,
      "loss": 0.4786,
      "step": 486
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00033431678352918384,
      "loss": 0.4302,
      "step": 487
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003339969525950361,
      "loss": 0.4914,
      "step": 488
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00033367649867903663,
      "loss": 0.4102,
      "step": 489
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003333554232710477,
      "loss": 0.4698,
      "step": 490
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003330337278638207,
      "loss": 0.4454,
      "step": 491
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00033271141395298964,
      "loss": 0.4648,
      "step": 492
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00033238848303706415,
      "loss": 0.4616,
      "step": 493
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00033206493661742237,
      "loss": 0.4861,
      "step": 494
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00033174077619830416,
      "loss": 0.4797,
      "step": 495
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00033141600328680373,
      "loss": 0.5104,
      "step": 496
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00033109061939286336,
      "loss": 0.5712,
      "step": 497
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00033076462602926553,
      "loss": 0.5425,
      "step": 498
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00033043802471162636,
      "loss": 0.6156,
      "step": 499
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003301108169583887,
      "loss": 0.4282,
      "step": 500
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003297830042908146,
      "loss": 0.4088,
      "step": 501
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00032945458823297857,
      "loss": 0.4866,
      "step": 502
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003291255703117605,
      "loss": 0.5045,
      "step": 503
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003287959520568384,
      "loss": 0.491,
      "step": 504
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00032846573500068136,
      "loss": 0.458,
      "step": 505
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00032813492067854246,
      "loss": 0.4508,
      "step": 506
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003278035106284516,
      "loss": 0.4294,
      "step": 507
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00032747150639120834,
      "loss": 0.4834,
      "step": 508
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00032713890951037477,
      "loss": 0.3857,
      "step": 509
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00032680572153226834,
      "loss": 0.4072,
      "step": 510
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003264719440059545,
      "loss": 0.4028,
      "step": 511
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00032613757848323977,
      "loss": 0.3789,
      "step": 512
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00032580262651866446,
      "loss": 0.4944,
      "step": 513
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003254670896694952,
      "loss": 0.4259,
      "step": 514
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00032513096949571805,
      "loss": 0.5037,
      "step": 515
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00032479426756003093,
      "loss": 0.5857,
      "step": 516
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003244569854278366,
      "loss": 0.5407,
      "step": 517
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00032411912466723524,
      "loss": 0.499,
      "step": 518
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003237806868490172,
      "loss": 0.4359,
      "step": 519
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00032344167354665573,
      "loss": 0.4374,
      "step": 520
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003231020863362997,
      "loss": 0.4172,
      "step": 521
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.000322761926796766,
      "loss": 0.4451,
      "step": 522
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0003224211965095326,
      "loss": 0.4,
      "step": 523
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0003220798970587309,
      "loss": 0.4009,
      "step": 524
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0003217380300311386,
      "loss": 0.3966,
      "step": 525
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.000321395597016172,
      "loss": 0.4255,
      "step": 526
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00032105259960587895,
      "loss": 0.4707,
      "step": 527
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00032070903939493124,
      "loss": 0.5313,
      "step": 528
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0003203649179806172,
      "loss": 0.3596,
      "step": 529
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0003200202369628345,
      "loss": 0.5223,
      "step": 530
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00031967499794408234,
      "loss": 0.4146,
      "step": 531
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00031932920252945423,
      "loss": 0.4328,
      "step": 532
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0003189828523266306,
      "loss": 0.4258,
      "step": 533
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00031863594894587105,
      "loss": 0.4457,
      "step": 534
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0003182884940000072,
      "loss": 0.5249,
      "step": 535
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0003179404891044348,
      "loss": 0.4751,
      "step": 536
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00031759193587710676,
      "loss": 0.5378,
      "step": 537
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00031724283593852497,
      "loss": 0.634,
      "step": 538
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00031689319091173326,
      "loss": 0.4298,
      "step": 539
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00031654300242230977,
      "loss": 0.5469,
      "step": 540
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00031619227209835917,
      "loss": 0.5153,
      "step": 541
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0003158410015705053,
      "loss": 0.4144,
      "step": 542
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0003154891924718837,
      "loss": 0.6041,
      "step": 543
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0003151368464381335,
      "loss": 0.4891,
      "step": 544
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0003147839651073904,
      "loss": 0.5258,
      "step": 545
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00031443055012027874,
      "loss": 0.4351,
      "step": 546
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.000314076603119904,
      "loss": 0.4556,
      "step": 547
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00031372212575184514,
      "loss": 0.5445,
      "step": 548
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00031336711966414675,
      "loss": 0.5585,
      "step": 549
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0003130115865073117,
      "loss": 0.367,
      "step": 550
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0003126555279342933,
      "loss": 0.4877,
      "step": 551
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0003122989456004876,
      "loss": 0.4335,
      "step": 552
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0003119418411637258,
      "loss": 0.4383,
      "step": 553
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0003115842162842663,
      "loss": 0.4508,
      "step": 554
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00031122607262478743,
      "loss": 0.4631,
      "step": 555
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0003108674118503793,
      "loss": 0.3496,
      "step": 556
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0003105082356285361,
      "loss": 0.4108,
      "step": 557
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0003101485456291486,
      "loss": 0.4877,
      "step": 558
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00030978834352449614,
      "loss": 0.3696,
      "step": 559
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00030942763098923913,
      "loss": 0.5138,
      "step": 560
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00030906640970041084,
      "loss": 0.5961,
      "step": 561
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0003087046813374099,
      "loss": 0.3824,
      "step": 562
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00030834244758199276,
      "loss": 0.4925,
      "step": 563
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.000307979710118265,
      "loss": 0.4511,
      "step": 564
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00030761647063267457,
      "loss": 0.4306,
      "step": 565
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0003072527308140031,
      "loss": 0.468,
      "step": 566
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00030688849235335856,
      "loss": 0.4842,
      "step": 567
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0003065237569441671,
      "loss": 0.4332,
      "step": 568
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00030615852628216537,
      "loss": 0.4637,
      "step": 569
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003057928020653925,
      "loss": 0.6193,
      "step": 570
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003054265859941824,
      "loss": 0.5033,
      "step": 571
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00030505987977115555,
      "loss": 0.4185,
      "step": 572
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003046926851012114,
      "loss": 0.4211,
      "step": 573
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003043250036915201,
      "loss": 0.5089,
      "step": 574
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00030395683725151505,
      "loss": 0.517,
      "step": 575
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003035881874928845,
      "loss": 0.492,
      "step": 576
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003032190561295636,
      "loss": 0.4535,
      "step": 577
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003028494448777269,
      "loss": 0.3947,
      "step": 578
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00030247935545577986,
      "loss": 0.3125,
      "step": 579
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0003021087895843511,
      "loss": 0.3882,
      "step": 580
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0003017377489862845,
      "loss": 0.4802,
      "step": 581
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00030136623538663083,
      "loss": 0.4652,
      "step": 582
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00030099425051263994,
      "loss": 0.3816,
      "step": 583
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0003006217960937529,
      "loss": 0.4583,
      "step": 584
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00030024887386159385,
      "loss": 0.4568,
      "step": 585
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00029987548554996174,
      "loss": 0.3908,
      "step": 586
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002995016328948225,
      "loss": 0.4235,
      "step": 587
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00029912731763430075,
      "loss": 0.4138,
      "step": 588
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00029875254150867216,
      "loss": 0.5838,
      "step": 589
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002983773062603548,
      "loss": 0.462,
      "step": 590
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00029800161363390145,
      "loss": 0.4632,
      "step": 591
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00029762546537599125,
      "loss": 0.5898,
      "step": 592
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002972488632354218,
      "loss": 0.4742,
      "step": 593
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00029687180896310065,
      "loss": 0.4579,
      "step": 594
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002964943043120378,
      "loss": 0.5514,
      "step": 595
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00029611635103733675,
      "loss": 0.4304,
      "step": 596
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002957379508961871,
      "loss": 0.4383,
      "step": 597
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00029535910564785584,
      "loss": 0.5327,
      "step": 598
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00029497981705367933,
      "loss": 0.4781,
      "step": 599
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00029460008687705525,
      "loss": 0.4178,
      "step": 600
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002942199168834342,
      "loss": 0.3987,
      "step": 601
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00029383930884031183,
      "loss": 0.3861,
      "step": 602
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00029345826451722005,
      "loss": 0.5322,
      "step": 603
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00029307678568571936,
      "loss": 0.3997,
      "step": 604
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002926948741193903,
      "loss": 0.4121,
      "step": 605
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00029231253159382514,
      "loss": 0.4931,
      "step": 606
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00029192975988662017,
      "loss": 0.4626,
      "step": 607
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00029154656077736666,
      "loss": 0.4441,
      "step": 608
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002911629360476432,
      "loss": 0.3863,
      "step": 609
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00029077888748100703,
      "loss": 0.36,
      "step": 610
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00029039441686298594,
      "loss": 0.4246,
      "step": 611
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002900095259810702,
      "loss": 0.4916,
      "step": 612
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00028962421662470346,
      "loss": 0.4896,
      "step": 613
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00028923849058527535,
      "loss": 0.4237,
      "step": 614
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00028885234965611274,
      "loss": 0.5727,
      "step": 615
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00028846579563247116,
      "loss": 0.5681,
      "step": 616
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002880788303115269,
      "loss": 0.4383,
      "step": 617
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00028769145549236845,
      "loss": 0.4962,
      "step": 618
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002873036729759881,
      "loss": 0.5472,
      "step": 619
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002869154845652738,
      "loss": 0.5431,
      "step": 620
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002865268920650003,
      "loss": 0.4152,
      "step": 621
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002861378972818211,
      "loss": 0.3922,
      "step": 622
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002857485020242602,
      "loss": 0.5129,
      "step": 623
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002853587081027034,
      "loss": 0.4328,
      "step": 624
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00028496851732938997,
      "loss": 0.4431,
      "step": 625
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002845779315184042,
      "loss": 0.4968,
      "step": 626
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.000284186952485667,
      "loss": 0.5301,
      "step": 627
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002837955820489276,
      "loss": 0.4332,
      "step": 628
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002834038220277546,
      "loss": 0.4245,
      "step": 629
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00028301167424352836,
      "loss": 0.5057,
      "step": 630
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00028261914051943166,
      "loss": 0.4623,
      "step": 631
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00028222622268044174,
      "loss": 0.5452,
      "step": 632
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00028183292255332164,
      "loss": 0.5238,
      "step": 633
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00028143924196661176,
      "loss": 0.3966,
      "step": 634
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002810451827506214,
      "loss": 0.35,
      "step": 635
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00028065074673742007,
      "loss": 0.4325,
      "step": 636
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002802559357608292,
      "loss": 0.4854,
      "step": 637
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00027986075165641343,
      "loss": 0.4254,
      "step": 638
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00027946519626147225,
      "loss": 0.4614,
      "step": 639
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00027906927141503125,
      "loss": 0.3798,
      "step": 640
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00027867297895783373,
      "loss": 0.4742,
      "step": 641
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002782763207323322,
      "loss": 0.4007,
      "step": 642
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002778792985826795,
      "loss": 0.4383,
      "step": 643
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002774819143547206,
      "loss": 0.4298,
      "step": 644
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00027708416989598387,
      "loss": 0.5178,
      "step": 645
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002766860670556722,
      "loss": 0.3434,
      "step": 646
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002762876076846551,
      "loss": 0.3862,
      "step": 647
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00027588879363545934,
      "loss": 0.4459,
      "step": 648
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002754896267622608,
      "loss": 0.3934,
      "step": 649
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00027509010892087565,
      "loss": 0.4349,
      "step": 650
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.000274690241968752,
      "loss": 0.4178,
      "step": 651
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002742900277649607,
      "loss": 0.4151,
      "step": 652
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002738894681701874,
      "loss": 0.3888,
      "step": 653
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00027348856504672323,
      "loss": 0.4214,
      "step": 654
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002730873202584567,
      "loss": 0.519,
      "step": 655
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00027268573567086477,
      "loss": 0.5463,
      "step": 656
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00027228381315100417,
      "loss": 0.3367,
      "step": 657
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00027188155456750256,
      "loss": 0.4629,
      "step": 658
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00027147896179055043,
      "loss": 0.4456,
      "step": 659
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002710760366918917,
      "loss": 0.4348,
      "step": 660
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002706727811448153,
      "loss": 0.4505,
      "step": 661
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002702691970241468,
      "loss": 0.5028,
      "step": 662
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00026986528620623904,
      "loss": 0.5257,
      "step": 663
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00026946105056896403,
      "loss": 0.4977,
      "step": 664
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00026905649199170377,
      "loss": 0.421,
      "step": 665
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002686516123553417,
      "loss": 0.4931,
      "step": 666
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00026824641354225397,
      "loss": 0.5818,
      "step": 667
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002678408974363005,
      "loss": 0.4211,
      "step": 668
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00026743506592281674,
      "loss": 0.5182,
      "step": 669
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00026702892088860413,
      "loss": 0.5591,
      "step": 670
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002666224642219221,
      "loss": 0.5363,
      "step": 671
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002662156978124786,
      "loss": 0.5866,
      "step": 672
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002658086235514218,
      "loss": 0.422,
      "step": 673
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002654012433313312,
      "loss": 0.5375,
      "step": 674
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002649935590462087,
      "loss": 0.4752,
      "step": 675
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00026458557259146986,
      "loss": 0.4271,
      "step": 676
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002641772858639351,
      "loss": 0.4843,
      "step": 677
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00026376870076182086,
      "loss": 0.4827,
      "step": 678
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00026335981918473086,
      "loss": 0.47,
      "step": 679
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002629506430336472,
      "loss": 0.368,
      "step": 680
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00026254117421092133,
      "loss": 0.481,
      "step": 681
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002621314146202656,
      "loss": 0.4153,
      "step": 682
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002617213661667443,
      "loss": 0.4397,
      "step": 683
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002613110307567643,
      "loss": 0.4052,
      "step": 684
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00026090041029806695,
      "loss": 0.4652,
      "step": 685
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00026048950669971884,
      "loss": 0.3826,
      "step": 686
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00026007832187210277,
      "loss": 0.5639,
      "step": 687
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00025966685772690906,
      "loss": 0.3917,
      "step": 688
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00025925511617712685,
      "loss": 0.5248,
      "step": 689
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002588430991370347,
      "loss": 0.3796,
      "step": 690
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002584308085221922,
      "loss": 0.4391,
      "step": 691
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00025801824624943084,
      "loss": 0.4514,
      "step": 692
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00025760541423684496,
      "loss": 0.5046,
      "step": 693
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002571923144037831,
      "loss": 0.4578,
      "step": 694
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002567789486708389,
      "loss": 0.4681,
      "step": 695
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00025636531895984236,
      "loss": 0.4501,
      "step": 696
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002559514271938506,
      "loss": 0.4411,
      "step": 697
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00025553727529713916,
      "loss": 0.401,
      "step": 698
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00025512286519519293,
      "loss": 0.4911,
      "step": 699
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002547081988146974,
      "loss": 0.3754,
      "step": 700
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00025429327808352946,
      "loss": 0.3807,
      "step": 701
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002538781049307486,
      "loss": 0.4193,
      "step": 702
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002534626812865876,
      "loss": 0.5259,
      "step": 703
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00025304700908244433,
      "loss": 0.3684,
      "step": 704
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002526310902508718,
      "loss": 0.5423,
      "step": 705
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002522149267255699,
      "loss": 0.4288,
      "step": 706
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.000251798520441376,
      "loss": 0.5046,
      "step": 707
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002513818733342564,
      "loss": 0.3777,
      "step": 708
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00025096498734129667,
      "loss": 0.5171,
      "step": 709
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002505478644006932,
      "loss": 0.3785,
      "step": 710
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00025013050645174414,
      "loss": 0.5413,
      "step": 711
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00024971291543483994,
      "loss": 0.5018,
      "step": 712
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00024929509329145477,
      "loss": 0.5212,
      "step": 713
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00024887704196413746,
      "loss": 0.483,
      "step": 714
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002484587633965023,
      "loss": 0.3684,
      "step": 715
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00024804025953322005,
      "loss": 0.3782,
      "step": 716
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00024762153232000877,
      "loss": 0.4995,
      "step": 717
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002472025837036253,
      "loss": 0.4324,
      "step": 718
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002467834156318555,
      "loss": 0.5203,
      "step": 719
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002463640300535057,
      "loss": 0.423,
      "step": 720
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002459444289183933,
      "loss": 0.4537,
      "step": 721
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00024552461417733817,
      "loss": 0.4124,
      "step": 722
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002451045877821528,
      "loss": 0.4865,
      "step": 723
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002446843516856343,
      "loss": 0.4845,
      "step": 724
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00024426390784155425,
      "loss": 0.4174,
      "step": 725
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00024384325820465033,
      "loss": 0.4456,
      "step": 726
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002434224047306169,
      "loss": 0.4429,
      "step": 727
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002430013493760961,
      "loss": 0.363,
      "step": 728
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00024258009409866853,
      "loss": 0.4769,
      "step": 729
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00024215864085684442,
      "loss": 0.4597,
      "step": 730
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00024173699161005429,
      "loss": 0.366,
      "step": 731
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00024131514831863995,
      "loss": 0.4746,
      "step": 732
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002408931129438453,
      "loss": 0.5608,
      "step": 733
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00024047088744780744,
      "loss": 0.4292,
      "step": 734
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00024004847379354726,
      "loss": 0.4743,
      "step": 735
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00023962587394496038,
      "loss": 0.3855,
      "step": 736
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00023920308986680834,
      "loss": 0.4573,
      "step": 737
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00023878012352470892,
      "loss": 0.3937,
      "step": 738
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002383569768851274,
      "loss": 0.4371,
      "step": 739
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00023793365191536735,
      "loss": 0.5432,
      "step": 740
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00023751015058356135,
      "loss": 0.4803,
      "step": 741
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.000237086474858662,
      "loss": 0.4281,
      "step": 742
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00023666262671043263,
      "loss": 0.4031,
      "step": 743
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00023623860810943826,
      "loss": 0.4725,
      "step": 744
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002358144210270364,
      "loss": 0.4644,
      "step": 745
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00023539006743536774,
      "loss": 0.4848,
      "step": 746
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00023496554930734718,
      "loss": 0.4084,
      "step": 747
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00023454086861665472,
      "loss": 0.4322,
      "step": 748
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00023411602733772595,
      "loss": 0.4847,
      "step": 749
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00023369102744574312,
      "loss": 0.4298,
      "step": 750
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00023326587091662603,
      "loss": 0.4268,
      "step": 751
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00023284055972702254,
      "loss": 0.4089,
      "step": 752
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002324150958542997,
      "loss": 0.4214,
      "step": 753
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00023198948127653446,
      "loss": 0.5576,
      "step": 754
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00023156371797250418,
      "loss": 0.4377,
      "step": 755
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00023113780792167785,
      "loss": 0.4934,
      "step": 756
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002307117531042068,
      "loss": 0.3698,
      "step": 757
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00023028555550091536,
      "loss": 0.4722,
      "step": 758
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00022985921709329157,
      "loss": 0.3837,
      "step": 759
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00022943273986347822,
      "loss": 0.5132,
      "step": 760
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002290061257942635,
      "loss": 0.487,
      "step": 761
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00022857937686907183,
      "loss": 0.3857,
      "step": 762
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00022815249507195445,
      "loss": 0.4135,
      "step": 763
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00022772548238758064,
      "loss": 0.4639,
      "step": 764
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00022729834080122791,
      "loss": 0.5297,
      "step": 765
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00022687107229877324,
      "loss": 0.4485,
      "step": 766
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00022644367886668357,
      "loss": 0.467,
      "step": 767
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00022601616249200675,
      "loss": 0.4304,
      "step": 768
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00022558852516236217,
      "loss": 0.5531,
      "step": 769
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00022516076886593158,
      "loss": 0.5021,
      "step": 770
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00022473289559144988,
      "loss": 0.433,
      "step": 771
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00022430490732819566,
      "loss": 0.505,
      "step": 772
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00022387680606598235,
      "loss": 0.4677,
      "step": 773
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00022344859379514858,
      "loss": 0.4421,
      "step": 774
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00022302027250654905,
      "loss": 0.4282,
      "step": 775
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002225918441915456,
      "loss": 0.366,
      "step": 776
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00022216331084199724,
      "loss": 0.4147,
      "step": 777
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00022173467445025158,
      "loss": 0.586,
      "step": 778
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00022130593700913522,
      "loss": 0.5285,
      "step": 779
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00022087710051194463,
      "loss": 0.4484,
      "step": 780
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002204481669524367,
      "loss": 0.4063,
      "step": 781
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002200191383248197,
      "loss": 0.4751,
      "step": 782
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00021959001662374373,
      "loss": 0.3936,
      "step": 783
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00021916080384429184,
      "loss": 0.4433,
      "step": 784
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002187315019819703,
      "loss": 0.4883,
      "step": 785
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00021830211303269965,
      "loss": 0.4925,
      "step": 786
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00021787263899280537,
      "loss": 0.4597,
      "step": 787
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00021744308185900848,
      "loss": 0.4954,
      "step": 788
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00021701344362841626,
      "loss": 0.4025,
      "step": 789
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00021658372629851318,
      "loss": 0.5734,
      "step": 790
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00021615393186715128,
      "loss": 0.3779,
      "step": 791
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00021572406233254116,
      "loss": 0.4994,
      "step": 792
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00021529411969324275,
      "loss": 0.5359,
      "step": 793
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00021486410594815554,
      "loss": 0.4738,
      "step": 794
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00021443402309650979,
      "loss": 0.4915,
      "step": 795
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00021400387313785704,
      "loss": 0.4991,
      "step": 796
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00021357365807206087,
      "loss": 0.4503,
      "step": 797
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002131433798992874,
      "loss": 0.4887,
      "step": 798
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00021271304061999633,
      "loss": 0.4279,
      "step": 799
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00021228264223493139,
      "loss": 0.5367,
      "step": 800
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00021185218674511097,
      "loss": 0.3212,
      "step": 801
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00021142167615181915,
      "loss": 0.493,
      "step": 802
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002109911124565962,
      "loss": 0.3635,
      "step": 803
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00021056049766122916,
      "loss": 0.3494,
      "step": 804
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00021012983376774254,
      "loss": 0.3536,
      "step": 805
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002096991227783895,
      "loss": 0.4335,
      "step": 806
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00020926836669564168,
      "loss": 0.4673,
      "step": 807
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00020883756752218075,
      "loss": 0.5269,
      "step": 808
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002084067272608886,
      "loss": 0.4365,
      "step": 809
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00020797584791483806,
      "loss": 0.2998,
      "step": 810
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00020754493148728375,
      "loss": 0.4318,
      "step": 811
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00020711397998165264,
      "loss": 0.3205,
      "step": 812
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00020668299540153493,
      "loss": 0.5026,
      "step": 813
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00020625197975067438,
      "loss": 0.3923,
      "step": 814
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002058209350329594,
      "loss": 0.3026,
      "step": 815
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00020538986325241342,
      "loss": 0.4729,
      "step": 816
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00020495876641318567,
      "loss": 0.3236,
      "step": 817
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002045276465195419,
      "loss": 0.4934,
      "step": 818
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00020409650557585523,
      "loss": 0.3791,
      "step": 819
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00020366534558659635,
      "loss": 0.3879,
      "step": 820
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00020323416855632477,
      "loss": 0.3807,
      "step": 821
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00020280297648967897,
      "loss": 0.415,
      "step": 822
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00020237177139136758,
      "loss": 0.3824,
      "step": 823
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002019405552661596,
      "loss": 0.3854,
      "step": 824
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00020150933011887543,
      "loss": 0.3781,
      "step": 825
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00020107809795437745,
      "loss": 0.3904,
      "step": 826
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00020064686077756057,
      "loss": 0.3213,
      "step": 827
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00020021562059334302,
      "loss": 0.4888,
      "step": 828
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00019978437940665702,
      "loss": 0.3375,
      "step": 829
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001993531392224394,
      "loss": 0.4325,
      "step": 830
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00019892190204562257,
      "loss": 0.2865,
      "step": 831
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001984906698811246,
      "loss": 0.3984,
      "step": 832
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00019805944473384038,
      "loss": 0.3011,
      "step": 833
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00019762822860863247,
      "loss": 0.4063,
      "step": 834
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00019719702351032105,
      "loss": 0.4489,
      "step": 835
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00019676583144367525,
      "loss": 0.3991,
      "step": 836
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00019633465441340367,
      "loss": 0.2736,
      "step": 837
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00019590349442414484,
      "loss": 0.3842,
      "step": 838
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001954723534804581,
      "loss": 0.346,
      "step": 839
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001950412335868144,
      "loss": 0.3435,
      "step": 840
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00019461013674758668,
      "loss": 0.4139,
      "step": 841
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00019417906496704064,
      "loss": 0.4031,
      "step": 842
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00019374802024932567,
      "loss": 0.352,
      "step": 843
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00019331700459846517,
      "loss": 0.332,
      "step": 844
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00019288602001834735,
      "loss": 0.3822,
      "step": 845
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00019245506851271632,
      "loss": 0.3912,
      "step": 846
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.000192024152085162,
      "loss": 0.4028,
      "step": 847
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00019159327273911145,
      "loss": 0.3625,
      "step": 848
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00019116243247781927,
      "loss": 0.392,
      "step": 849
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00019073163330435842,
      "loss": 0.3687,
      "step": 850
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00019030087722161055,
      "loss": 0.3794,
      "step": 851
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00018987016623225747,
      "loss": 0.4095,
      "step": 852
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00018943950233877094,
      "loss": 0.3665,
      "step": 853
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00018900888754340382,
      "loss": 0.3826,
      "step": 854
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0001885783238481809,
      "loss": 0.4903,
      "step": 855
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00018814781325488905,
      "loss": 0.3174,
      "step": 856
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00018771735776506866,
      "loss": 0.3987,
      "step": 857
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0001872869593800037,
      "loss": 0.4488,
      "step": 858
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00018685662010071261,
      "loss": 0.3298,
      "step": 859
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001864263419279392,
      "loss": 0.3385,
      "step": 860
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00018599612686214304,
      "loss": 0.4442,
      "step": 861
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00018556597690349023,
      "loss": 0.3132,
      "step": 862
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001851358940518445,
      "loss": 0.5051,
      "step": 863
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001847058803067573,
      "loss": 0.3919,
      "step": 864
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00018427593766745884,
      "loss": 0.4193,
      "step": 865
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001838460681328488,
      "loss": 0.3196,
      "step": 866
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00018341627370148692,
      "loss": 0.6047,
      "step": 867
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00018298655637158376,
      "loss": 0.3741,
      "step": 868
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00018255691814099157,
      "loss": 0.4033,
      "step": 869
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00018212736100719465,
      "loss": 0.422,
      "step": 870
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00018169788696730034,
      "loss": 0.3358,
      "step": 871
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00018126849801802976,
      "loss": 0.3295,
      "step": 872
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00018083919615570823,
      "loss": 0.4859,
      "step": 873
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00018040998337625627,
      "loss": 0.2917,
      "step": 874
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00017998086167518034,
      "loss": 0.3505,
      "step": 875
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00017955183304756332,
      "loss": 0.5962,
      "step": 876
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001791228994880554,
      "loss": 0.3097,
      "step": 877
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00017869406299086482,
      "loss": 0.4547,
      "step": 878
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001782653255497485,
      "loss": 0.4567,
      "step": 879
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0001778366891580028,
      "loss": 0.3815,
      "step": 880
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00017740815580845446,
      "loss": 0.5061,
      "step": 881
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00017697972749345094,
      "loss": 0.3729,
      "step": 882
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0001765514062048515,
      "loss": 0.3626,
      "step": 883
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00017612319393401772,
      "loss": 0.4256,
      "step": 884
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00017569509267180433,
      "loss": 0.4114,
      "step": 885
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00017526710440855017,
      "loss": 0.3554,
      "step": 886
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00017483923113406844,
      "loss": 0.4741,
      "step": 887
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00017441147483763785,
      "loss": 0.4472,
      "step": 888
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00017398383750799327,
      "loss": 0.4325,
      "step": 889
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00017355632113331648,
      "loss": 0.4184,
      "step": 890
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00017312892770122678,
      "loss": 0.468,
      "step": 891
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001727016591987721,
      "loss": 0.3996,
      "step": 892
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00017227451761241938,
      "loss": 0.4718,
      "step": 893
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00017184750492804554,
      "loss": 0.4076,
      "step": 894
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00017142062313092824,
      "loss": 0.337,
      "step": 895
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00017099387420573656,
      "loss": 0.3534,
      "step": 896
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001705672601365218,
      "loss": 0.4757,
      "step": 897
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00017014078290670848,
      "loss": 0.4629,
      "step": 898
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00016971444449908474,
      "loss": 0.4999,
      "step": 899
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001692882468957932,
      "loss": 0.4404,
      "step": 900
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001688621920783222,
      "loss": 0.4102,
      "step": 901
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00016843628202749592,
      "loss": 0.4285,
      "step": 902
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001680105187234656,
      "loss": 0.4326,
      "step": 903
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001675849041457003,
      "loss": 0.507,
      "step": 904
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00016715944027297753,
      "loss": 0.3976,
      "step": 905
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00016673412908337401,
      "loss": 0.4173,
      "step": 906
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0001663089725542569,
      "loss": 0.4053,
      "step": 907
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0001658839726622741,
      "loss": 0.4606,
      "step": 908
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00016545913138334535,
      "loss": 0.3376,
      "step": 909
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00016503445069265287,
      "loss": 0.4466,
      "step": 910
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00016460993256463228,
      "loss": 0.3034,
      "step": 911
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00016418557897296366,
      "loss": 0.4127,
      "step": 912
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00016376139189056176,
      "loss": 0.4437,
      "step": 913
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001633373732895674,
      "loss": 0.4479,
      "step": 914
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00016291352514133807,
      "loss": 0.4006,
      "step": 915
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00016248984941643873,
      "loss": 0.4428,
      "step": 916
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00016206634808463267,
      "loss": 0.3704,
      "step": 917
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00016164302311487262,
      "loss": 0.3807,
      "step": 918
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00016121987647529115,
      "loss": 0.4194,
      "step": 919
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00016079691013319168,
      "loss": 0.4486,
      "step": 920
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00016037412605503966,
      "loss": 0.3642,
      "step": 921
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00015995152620645287,
      "loss": 0.4344,
      "step": 922
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00015952911255219258,
      "loss": 0.3868,
      "step": 923
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00015910688705615472,
      "loss": 0.4161,
      "step": 924
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00015868485168136015,
      "loss": 0.4094,
      "step": 925
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00015826300838994573,
      "loss": 0.4528,
      "step": 926
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00015784135914315563,
      "loss": 0.3656,
      "step": 927
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00015741990590133152,
      "loss": 0.4982,
      "step": 928
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00015699865062390392,
      "loss": 0.4157,
      "step": 929
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00015657759526938313,
      "loss": 0.3153,
      "step": 930
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00015615674179534977,
      "loss": 0.4343,
      "step": 931
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00015573609215844582,
      "loss": 0.4922,
      "step": 932
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001553156483143658,
      "loss": 0.5049,
      "step": 933
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00015489541221784726,
      "loss": 0.4128,
      "step": 934
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00015447538582266193,
      "loss": 0.3353,
      "step": 935
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00015405557108160673,
      "loss": 0.4553,
      "step": 936
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00015363596994649433,
      "loss": 0.406,
      "step": 937
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00015321658436814455,
      "loss": 0.4339,
      "step": 938
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00015279741629637477,
      "loss": 0.4105,
      "step": 939
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00015237846767999122,
      "loss": 0.4491,
      "step": 940
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00015195974046678003,
      "loss": 0.3728,
      "step": 941
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00015154123660349774,
      "loss": 0.3357,
      "step": 942
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00015112295803586256,
      "loss": 0.3035,
      "step": 943
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00015070490670854528,
      "loss": 0.347,
      "step": 944
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00015028708456516017,
      "loss": 0.4472,
      "step": 945
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014986949354825588,
      "loss": 0.3888,
      "step": 946
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014945213559930677,
      "loss": 0.4407,
      "step": 947
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014903501265870338,
      "loss": 0.5161,
      "step": 948
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014861812666574364,
      "loss": 0.4002,
      "step": 949
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.000148201479558624,
      "loss": 0.3079,
      "step": 950
    }
  ],
  "logging_steps": 1,
  "max_steps": 1557,
  "num_train_epochs": 3,
  "save_steps": 50,
  "total_flos": 1.2732085224403108e+18,
  "trial_name": null,
  "trial_params": null
}