Precision: [tensor(0.9998, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9992, device='cuda:0')]

Output distance: [tensor(153459.9531, device='cuda:0'), tensor(144486.0625, device='cuda:0'), tensor(143934.4062, device='cuda:0'), tensor(166655.3750, device='cuda:0'), tensor(139504.0938, device='cuda:0'), tensor(141328.9688, device='cuda:0'), tensor(139482.8438, device='cuda:0'), tensor(146193.5312, device='cuda:0'), tensor(145333.4219, device='cuda:0'), tensor(141075.2031, device='cuda:0')]

Prediction loss: [tensor(156079.3594, device='cuda:0'), tensor(146096.1875, device='cuda:0'), tensor(138996.9844, device='cuda:0'), tensor(179456.8125, device='cuda:0'), tensor(133702.0938, device='cuda:0'), tensor(142414.2969, device='cuda:0'), tensor(137744.3438, device='cuda:0'), tensor(144241.7344, device='cuda:0'), tensor(146973.2812, device='cuda:0'), tensor(137391.0156, device='cuda:0')]

Others: [{'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 17, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 25, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 25, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(1.9664e+08, device='cuda:0'), tensor(1.9325e+08, device='cuda:0'), tensor(1.9638e+08, device='cuda:0'), tensor(1.9714e+08, device='cuda:0'), tensor(1.9248e+08, device='cuda:0'), tensor(1.9352e+08, device='cuda:0'), tensor(1.9053e+08, device='cuda:0'), tensor(1.9143e+08, device='cuda:0'), tensor(1.9275e+08, device='cuda:0'), tensor(1.9035e+08, device='cuda:0')]

Training loss: 191986928.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=510594), datetime.timedelta(seconds=1, microseconds=548432), datetime.timedelta(seconds=1, microseconds=538478), datetime.timedelta(seconds=1, microseconds=533497), datetime.timedelta(seconds=1, microseconds=9722), datetime.timedelta(seconds=1, microseconds=331352), datetime.timedelta(seconds=1, microseconds=532502), datetime.timedelta(seconds=1, microseconds=529512), datetime.timedelta(seconds=1, microseconds=538472), datetime.timedelta(seconds=1, microseconds=360234)]

Phi time: [datetime.timedelta(seconds=1, microseconds=398325), datetime.timedelta(microseconds=852298), datetime.timedelta(microseconds=787087), datetime.timedelta(microseconds=786612), datetime.timedelta(microseconds=790353), datetime.timedelta(microseconds=788584), datetime.timedelta(microseconds=814745), datetime.timedelta(microseconds=790797), datetime.timedelta(microseconds=784915), datetime.timedelta(microseconds=793202)]

