Precision: [tensor(0.9995, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9997, 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(0.9997, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9998, device='cuda:0')]

Output distance: [tensor(141002.5938, device='cuda:0'), tensor(140422.1562, device='cuda:0'), tensor(140407.7031, device='cuda:0'), tensor(140535.6719, device='cuda:0'), tensor(140874.4844, device='cuda:0'), tensor(141000.2812, device='cuda:0'), tensor(140870.3438, device='cuda:0'), tensor(140874.6406, device='cuda:0'), tensor(143301.2188, device='cuda:0'), tensor(141018.1562, device='cuda:0')]

Prediction loss: [tensor(134803.1094, device='cuda:0'), tensor(134499.5469, device='cuda:0'), tensor(131529.7344, device='cuda:0'), tensor(134024.5781, device='cuda:0'), tensor(139970.7969, device='cuda:0'), tensor(145393.2188, device='cuda:0'), tensor(134140.9531, device='cuda:0'), tensor(135961.7031, device='cuda:0'), tensor(125540.0234, device='cuda:0'), tensor(136615.1719, device='cuda:0')]

Others: [{'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': 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': 13, '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')}]

Compressed training loss: [tensor(1.9263e+08, device='cuda:0'), tensor(1.9212e+08, device='cuda:0'), tensor(1.8695e+08, device='cuda:0'), tensor(1.8989e+08, device='cuda:0'), tensor(1.9361e+08, device='cuda:0'), tensor(1.9735e+08, device='cuda:0'), tensor(1.8927e+08, device='cuda:0'), tensor(1.9104e+08, device='cuda:0'), tensor(1.8608e+08, device='cuda:0'), tensor(1.9296e+08, device='cuda:0')]

Training loss: 192579808.0

Prediction time: [datetime.timedelta(microseconds=552657), datetime.timedelta(microseconds=601447), datetime.timedelta(microseconds=636301), datetime.timedelta(microseconds=639288), datetime.timedelta(microseconds=583525), datetime.timedelta(microseconds=576555), datetime.timedelta(microseconds=582530), datetime.timedelta(microseconds=581532), datetime.timedelta(microseconds=703016), datetime.timedelta(microseconds=575556)]

Phi time: [datetime.timedelta(seconds=1, microseconds=335256), datetime.timedelta(microseconds=797966), datetime.timedelta(microseconds=724398), datetime.timedelta(microseconds=732851), datetime.timedelta(microseconds=730253), datetime.timedelta(microseconds=729967), datetime.timedelta(microseconds=731223), datetime.timedelta(microseconds=727002), datetime.timedelta(microseconds=727829), datetime.timedelta(microseconds=731846)]

