Precision: [tensor(0.8562, device='cuda:0'), tensor(0.8571, device='cuda:0'), tensor(0.8567, device='cuda:0'), tensor(0.8564, device='cuda:0'), tensor(0.8564, device='cuda:0'), tensor(0.8555, device='cuda:0'), tensor(0.8572, device='cuda:0'), tensor(0.8571, device='cuda:0'), tensor(0.8568, device='cuda:0'), tensor(0.8586, device='cuda:0')]

Output distance: [tensor(570.4692, device='cuda:0'), tensor(550.6448, device='cuda:0'), tensor(560.9802, device='cuda:0'), tensor(549.8978, device='cuda:0'), tensor(552.5853, device='cuda:0'), tensor(592.8019, device='cuda:0'), tensor(564.1114, device='cuda:0'), tensor(552.5569, device='cuda:0'), tensor(550.5784, device='cuda:0'), tensor(545.1769, device='cuda:0')]

Prediction loss: [tensor(625.5870, device='cuda:0'), tensor(610.3096, device='cuda:0'), tensor(612.3777, device='cuda:0'), tensor(585.8881, device='cuda:0'), tensor(594.7402, device='cuda:0'), tensor(631.4841, device='cuda:0'), tensor(628.7100, device='cuda:0'), tensor(605.6915, device='cuda:0'), tensor(595.4590, device='cuda:0'), tensor(601.8087, device='cuda:0')]

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

Compressed training loss: [tensor(9049517., device='cuda:0'), tensor(8882883., device='cuda:0'), tensor(8888237., device='cuda:0'), tensor(8630107., device='cuda:0'), tensor(8721928., device='cuda:0'), tensor(8971868., device='cuda:0'), tensor(8993562., device='cuda:0'), tensor(8845202., device='cuda:0'), tensor(8736623., device='cuda:0'), tensor(8783999., device='cuda:0')]

Training loss: 8876262.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=666223), datetime.timedelta(seconds=1, microseconds=719191), datetime.timedelta(seconds=1, microseconds=709979), datetime.timedelta(seconds=1, microseconds=684374), datetime.timedelta(seconds=1, microseconds=708496), datetime.timedelta(seconds=1, microseconds=703046), datetime.timedelta(seconds=1, microseconds=702020), datetime.timedelta(seconds=1, microseconds=699947), datetime.timedelta(seconds=1, microseconds=692570), datetime.timedelta(seconds=1, microseconds=696914)]

Phi time: [datetime.timedelta(seconds=1, microseconds=333727), datetime.timedelta(microseconds=846716), datetime.timedelta(microseconds=824452), datetime.timedelta(microseconds=824086), datetime.timedelta(microseconds=827861), datetime.timedelta(microseconds=815722), datetime.timedelta(microseconds=849598), datetime.timedelta(microseconds=811469), datetime.timedelta(microseconds=826177), datetime.timedelta(microseconds=831723)]

