Precision: [tensor(0.9995, device='cuda:0'), tensor(0.9985, device='cuda:0'), tensor(0.9988, device='cuda:0'), tensor(0.9988, device='cuda:0'), tensor(0.9990, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9992, device='cuda:0'), tensor(0.9985, device='cuda:0'), tensor(0.9993, device='cuda:0')]

Output distance: [tensor(147537.0156, device='cuda:0'), tensor(145699.2031, device='cuda:0'), tensor(145636.0469, device='cuda:0'), tensor(145306.5625, device='cuda:0'), tensor(153644.5156, device='cuda:0'), tensor(149456.3125, device='cuda:0'), tensor(146040.0469, device='cuda:0'), tensor(145853.1562, device='cuda:0'), tensor(156944.4531, device='cuda:0'), tensor(145880.7812, device='cuda:0')]

Prediction loss: [tensor(140227.2344, device='cuda:0'), tensor(151025.8281, device='cuda:0'), tensor(143860.3438, device='cuda:0'), tensor(146968.8281, device='cuda:0'), tensor(126387.4453, device='cuda:0'), tensor(135462.7188, device='cuda:0'), tensor(147176.5312, device='cuda:0'), tensor(132045.8750, device='cuda:0'), tensor(126850.5703, device='cuda:0'), tensor(141857.6094, device='cuda:0')]

Others: [{'iter_num': 13, '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': 11, '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': 15, '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': 17, '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(2.0004e+08, device='cuda:0'), tensor(2.0194e+08, device='cuda:0'), tensor(1.9352e+08, device='cuda:0'), tensor(1.9988e+08, device='cuda:0'), tensor(1.8665e+08, device='cuda:0'), tensor(1.9171e+08, device='cuda:0'), tensor(1.9619e+08, device='cuda:0'), tensor(1.8942e+08, device='cuda:0'), tensor(1.8505e+08, device='cuda:0'), tensor(1.9199e+08, device='cuda:0')]

Training loss: 192354416.0

Prediction time: [datetime.timedelta(microseconds=530029), datetime.timedelta(microseconds=521721), datetime.timedelta(microseconds=504081), datetime.timedelta(microseconds=526836), datetime.timedelta(microseconds=642612), datetime.timedelta(microseconds=617051), datetime.timedelta(microseconds=464710), datetime.timedelta(microseconds=546072), datetime.timedelta(microseconds=631017), datetime.timedelta(microseconds=519004)]

Phi time: [datetime.timedelta(seconds=1, microseconds=90975), datetime.timedelta(microseconds=636777), datetime.timedelta(microseconds=567353), datetime.timedelta(microseconds=552556), datetime.timedelta(microseconds=571009), datetime.timedelta(microseconds=553148), datetime.timedelta(microseconds=551155), datetime.timedelta(microseconds=578010), datetime.timedelta(microseconds=563811), datetime.timedelta(microseconds=557144)]

