Precision: [tensor(0.9990, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9990, device='cuda:0'), tensor(0.9987, device='cuda:0'), tensor(0.9987, device='cuda:0'), tensor(0.9988, device='cuda:0'), tensor(0.9987, device='cuda:0'), tensor(0.9990, device='cuda:0'), tensor(0.9990, device='cuda:0'), tensor(0.9990, device='cuda:0')]

Output distance: [tensor(23037.9219, device='cuda:0'), tensor(23127.5508, device='cuda:0'), tensor(23294.1484, device='cuda:0'), tensor(23318.4590, device='cuda:0'), tensor(23094.4961, device='cuda:0'), tensor(23579.0723, device='cuda:0'), tensor(22967.4434, device='cuda:0'), tensor(23563.2207, device='cuda:0'), tensor(23295.3516, device='cuda:0'), tensor(23492.4883, device='cuda:0')]

Prediction loss: [tensor(22857.5547, device='cuda:0'), tensor(21781.3789, device='cuda:0'), tensor(25618.8789, device='cuda:0'), tensor(25544.4434, device='cuda:0'), tensor(24310.4023, device='cuda:0'), tensor(22710.5605, device='cuda:0'), tensor(22407.1777, device='cuda:0'), tensor(21922.2363, device='cuda:0'), tensor(20398.9688, device='cuda:0'), tensor(23440.8262, device='cuda:0')]

Others: [{'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': 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': 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': 13, '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': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(8795630., device='cuda:0'), tensor(8933225., device='cuda:0'), tensor(9556305., device='cuda:0'), tensor(9210766., device='cuda:0'), tensor(9141585., device='cuda:0'), tensor(8702461., device='cuda:0'), tensor(8712420., device='cuda:0'), tensor(8837944., device='cuda:0'), tensor(8325583.5000, device='cuda:0'), tensor(9030458., device='cuda:0')]

Training loss: 8827640.0

Prediction time: [datetime.timedelta(microseconds=531709), datetime.timedelta(microseconds=553667), datetime.timedelta(microseconds=553666), datetime.timedelta(microseconds=554663), datetime.timedelta(microseconds=493919), datetime.timedelta(microseconds=589514), datetime.timedelta(microseconds=528775), datetime.timedelta(microseconds=588571), datetime.timedelta(microseconds=635322), datetime.timedelta(microseconds=540774)]

Phi time: [datetime.timedelta(seconds=1, microseconds=246307), datetime.timedelta(microseconds=727598), datetime.timedelta(microseconds=632204), datetime.timedelta(microseconds=656219), datetime.timedelta(microseconds=647564), datetime.timedelta(microseconds=647834), datetime.timedelta(microseconds=633691), datetime.timedelta(microseconds=636590), datetime.timedelta(microseconds=630857), datetime.timedelta(microseconds=634537)]

