Precision: [tensor(0.8534, device='cuda:0'), tensor(0.8537, device='cuda:0'), tensor(0.8521, device='cuda:0'), tensor(0.8542, device='cuda:0'), tensor(0.8546, device='cuda:0'), tensor(0.8504, device='cuda:0'), tensor(0.8549, device='cuda:0'), tensor(0.8544, device='cuda:0'), tensor(0.8536, device='cuda:0'), tensor(0.8532, device='cuda:0')]

Output distance: [tensor(1195.3647, device='cuda:0'), tensor(646.5515, device='cuda:0'), tensor(635.2083, device='cuda:0'), tensor(573.6261, device='cuda:0'), tensor(1545.2948, device='cuda:0'), tensor(1567.4491, device='cuda:0'), tensor(576.6878, device='cuda:0'), tensor(686.6202, device='cuda:0'), tensor(585.6202, device='cuda:0'), tensor(561.3737, device='cuda:0')]

Prediction loss: [tensor(1446.8822, device='cuda:0'), tensor(692.4016, device='cuda:0'), tensor(672.9931, device='cuda:0'), tensor(613.4962, device='cuda:0'), tensor(1903.7815, device='cuda:0'), tensor(1892.0634, device='cuda:0'), tensor(618.2415, device='cuda:0'), tensor(762.8727, device='cuda:0'), tensor(627.7994, device='cuda:0'), tensor(595.6791, 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(17997, 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(8965208., device='cuda:0'), tensor(9005986., device='cuda:0'), tensor(9067821., device='cuda:0'), tensor(8779668., device='cuda:0'), tensor(8820192., device='cuda:0'), tensor(9140210., device='cuda:0'), tensor(8806646., device='cuda:0'), tensor(8865627., device='cuda:0'), tensor(8859294., device='cuda:0'), tensor(8729828., device='cuda:0')]

Training loss: 8852495.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=648012), datetime.timedelta(seconds=1, microseconds=670914), datetime.timedelta(seconds=1, microseconds=678879), datetime.timedelta(seconds=1, microseconds=682863), datetime.timedelta(seconds=1, microseconds=692823), datetime.timedelta(seconds=1, microseconds=677884), datetime.timedelta(seconds=1, microseconds=665935), datetime.timedelta(seconds=1, microseconds=662946), datetime.timedelta(seconds=1, microseconds=672906), datetime.timedelta(seconds=1, microseconds=674897)]

Phi time: [datetime.timedelta(seconds=1, microseconds=421517), datetime.timedelta(microseconds=857162), datetime.timedelta(microseconds=814346), datetime.timedelta(microseconds=806953), datetime.timedelta(microseconds=827033), datetime.timedelta(microseconds=807624), datetime.timedelta(microseconds=810363), datetime.timedelta(microseconds=820124), datetime.timedelta(microseconds=804890), datetime.timedelta(microseconds=798681)]

