Precision: [tensor(0.5363, device='cuda:0'), tensor(0.5394, device='cuda:0'), tensor(0.5432, device='cuda:0'), tensor(0.5385, device='cuda:0'), tensor(0.5485, device='cuda:0'), tensor(0.5583, device='cuda:0'), tensor(0.5459, device='cuda:0'), tensor(0.5496, device='cuda:0'), tensor(0.5432, device='cuda:0'), tensor(0.5437, device='cuda:0')]
Output distance: [tensor(18.9528, device='cuda:0'), tensor(18.9465, device='cuda:0'), tensor(18.9389, device='cuda:0'), tensor(18.9483, device='cuda:0'), tensor(18.9284, device='cuda:0'), tensor(18.9087, device='cuda:0'), tensor(18.9335, device='cuda:0'), tensor(18.9262, device='cuda:0'), tensor(18.9389, device='cuda:0'), tensor(18.9380, device='cuda:0')]
Prediction loss: [tensor(108.3922, device='cuda:0'), tensor(108.4926, device='cuda:0'), tensor(108.9846, device='cuda:0'), tensor(108.6702, device='cuda:0'), tensor(108.8587, device='cuda:0'), tensor(109.0077, device='cuda:0'), tensor(108.9324, device='cuda:0'), tensor(109.2357, device='cuda:0'), tensor(108.4195, device='cuda:0'), tensor(109.6297, 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=509673), datetime.timedelta(seconds=2, microseconds=500069), datetime.timedelta(seconds=2, microseconds=468629), datetime.timedelta(seconds=2, microseconds=510618), datetime.timedelta(seconds=2, microseconds=508579), datetime.timedelta(seconds=2, microseconds=503537), datetime.timedelta(seconds=2, microseconds=494045), datetime.timedelta(seconds=2, microseconds=574147), datetime.timedelta(seconds=2, microseconds=505300), datetime.timedelta(seconds=2, microseconds=483057)]
Phi time: [datetime.timedelta(seconds=97, microseconds=385245), datetime.timedelta(seconds=97, microseconds=324446), datetime.timedelta(seconds=97, microseconds=296425), datetime.timedelta(seconds=97, microseconds=263689), datetime.timedelta(seconds=97, microseconds=437955), datetime.timedelta(seconds=97, microseconds=501264), datetime.timedelta(seconds=97, microseconds=283422), datetime.timedelta(seconds=97, microseconds=476268), datetime.timedelta(seconds=99, microseconds=758717), datetime.timedelta(seconds=97, microseconds=438230)]
