Precision: [tensor(0.5426, device='cuda:0'), tensor(0.5437, device='cuda:0'), tensor(0.5425, device='cuda:0'), tensor(0.5269, device='cuda:0'), tensor(0.5363, device='cuda:0'), tensor(0.5550, device='cuda:0'), tensor(0.5532, device='cuda:0'), tensor(0.5401, device='cuda:0'), tensor(0.5490, device='cuda:0'), tensor(0.5466, device='cuda:0')]
Output distance: [tensor(18.9401, device='cuda:0'), tensor(18.9380, device='cuda:0'), tensor(18.9404, device='cuda:0'), tensor(18.9716, device='cuda:0'), tensor(18.9528, device='cuda:0'), tensor(18.9154, device='cuda:0'), tensor(18.9190, device='cuda:0'), tensor(18.9453, device='cuda:0'), tensor(18.9274, device='cuda:0'), tensor(18.9323, device='cuda:0')]
Prediction loss: [tensor(108.6453, device='cuda:0'), tensor(108.6281, device='cuda:0'), tensor(109.0010, device='cuda:0'), tensor(108.4947, device='cuda:0'), tensor(109.0863, device='cuda:0'), tensor(109.7579, device='cuda:0'), tensor(109.3804, device='cuda:0'), tensor(109.6870, device='cuda:0'), tensor(108.7444, device='cuda:0'), tensor(109.0081, device='cuda:0')]
Others: [{'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}]
Compressed training loss: [tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0'), tensor(0.0001, device='cuda:0')]
Training loss: 0
Prediction time: [datetime.timedelta(seconds=2, microseconds=583499), datetime.timedelta(seconds=2, microseconds=583061), datetime.timedelta(seconds=2, microseconds=583347), datetime.timedelta(seconds=2, microseconds=566594), datetime.timedelta(seconds=2, microseconds=583282), datetime.timedelta(seconds=2, microseconds=582853), datetime.timedelta(seconds=2, microseconds=583212), datetime.timedelta(seconds=2, microseconds=583109), datetime.timedelta(seconds=2, microseconds=600409), datetime.timedelta(seconds=2, microseconds=599720)]
Phi time: [datetime.timedelta(seconds=99, microseconds=411427), datetime.timedelta(seconds=99, microseconds=585328), datetime.timedelta(seconds=99, microseconds=369882), datetime.timedelta(seconds=99, microseconds=636504), datetime.timedelta(seconds=99, microseconds=417142), datetime.timedelta(seconds=99, microseconds=333088), datetime.timedelta(seconds=99, microseconds=332926), datetime.timedelta(seconds=99, microseconds=350568), datetime.timedelta(seconds=99, microseconds=467316), datetime.timedelta(seconds=99, microseconds=664852)]
