Precision: [tensor(0.9997, device='cuda:0'), tensor(1., device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9998, device='cuda:0')]

Output distance: [tensor(142398.1250, device='cuda:0'), tensor(142226.7344, device='cuda:0'), tensor(142054.9219, device='cuda:0'), tensor(142193.5000, device='cuda:0'), tensor(142430.1406, device='cuda:0'), tensor(143101.8281, device='cuda:0'), tensor(143832.6562, device='cuda:0'), tensor(142152.8906, device='cuda:0'), tensor(142132.0312, device='cuda:0'), tensor(142671.5312, device='cuda:0')]

Prediction loss: [tensor(134108.9531, device='cuda:0'), tensor(136559.6719, device='cuda:0'), tensor(141731.7656, device='cuda:0'), tensor(144976.1562, device='cuda:0'), tensor(141009.1719, device='cuda:0'), tensor(137258.9062, device='cuda:0'), tensor(138136.5312, device='cuda:0'), tensor(138162.8594, device='cuda:0'), tensor(147233.5312, device='cuda:0'), tensor(140969.8594, device='cuda:0')]

Others: [{'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(1.9111e+08, device='cuda:0'), tensor(1.9237e+08, device='cuda:0'), tensor(1.9276e+08, device='cuda:0'), tensor(1.9472e+08, device='cuda:0'), tensor(1.9194e+08, device='cuda:0'), tensor(1.8951e+08, device='cuda:0'), tensor(1.8941e+08, device='cuda:0'), tensor(1.8999e+08, device='cuda:0'), tensor(1.9636e+08, device='cuda:0'), tensor(1.9236e+08, device='cuda:0')]

Training loss: 192295984.0

Prediction time: [datetime.timedelta(microseconds=711008), datetime.timedelta(microseconds=652253), datetime.timedelta(microseconds=654246), datetime.timedelta(microseconds=641301), datetime.timedelta(microseconds=640306), datetime.timedelta(microseconds=729931), datetime.timedelta(microseconds=712003), datetime.timedelta(microseconds=652249), datetime.timedelta(microseconds=638314), datetime.timedelta(microseconds=711980)]

Phi time: [datetime.timedelta(seconds=1, microseconds=456252), datetime.timedelta(microseconds=901569), datetime.timedelta(microseconds=844554), datetime.timedelta(microseconds=850527), datetime.timedelta(microseconds=846032), datetime.timedelta(microseconds=850849), datetime.timedelta(microseconds=851569), datetime.timedelta(microseconds=848931), datetime.timedelta(microseconds=846222), datetime.timedelta(microseconds=852078)]

