Precision: [tensor(0.7020, device='cuda:0'), tensor(0.7041, device='cuda:0'), tensor(0.7104, device='cuda:0'), tensor(0.7104, device='cuda:0'), tensor(0.7046, device='cuda:0'), tensor(0.7075, device='cuda:0'), tensor(0.7031, device='cuda:0'), tensor(0.7088, device='cuda:0'), tensor(0.7039, device='cuda:0'), tensor(0.7036, device='cuda:0')]
Output distance: [tensor(4.9021, device='cuda:0'), tensor(4.8979, device='cuda:0'), tensor(4.8853, device='cuda:0'), tensor(4.8853, device='cuda:0'), tensor(4.8968, device='cuda:0'), tensor(4.8910, device='cuda:0'), tensor(4.9000, device='cuda:0'), tensor(4.8884, device='cuda:0'), tensor(4.8984, device='cuda:0'), tensor(4.8989, device='cuda:0')]
Prediction loss: [tensor(37.9781, device='cuda:0'), tensor(35.6376, device='cuda:0'), tensor(36.2439, device='cuda:0'), tensor(35.9126, device='cuda:0'), tensor(35.3271, device='cuda:0'), tensor(36.2355, device='cuda:0'), tensor(36.3756, device='cuda:0'), tensor(37.3342, device='cuda:0'), tensor(37.4774, device='cuda:0'), tensor(38.1875, device='cuda:0')]
Others: [{'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]
Compressed training loss: [tensor(48982.6328, device='cuda:0'), tensor(48788.2109, device='cuda:0'), tensor(48827.8984, device='cuda:0'), tensor(48786.3398, device='cuda:0'), tensor(49039.3906, device='cuda:0'), tensor(48925.8398, device='cuda:0'), tensor(48877.0820, device='cuda:0'), tensor(48951.9414, device='cuda:0'), tensor(48843.0312, device='cuda:0'), tensor(48838.6328, device='cuda:0')]
Training loss: 0
Prediction time: [datetime.timedelta(seconds=6, microseconds=281353), datetime.timedelta(seconds=6, microseconds=477515), datetime.timedelta(seconds=6, microseconds=242512), datetime.timedelta(seconds=6, microseconds=493429), datetime.timedelta(seconds=6, microseconds=243510), datetime.timedelta(seconds=6, microseconds=522320), datetime.timedelta(seconds=6, microseconds=232559), datetime.timedelta(seconds=6, microseconds=241516), datetime.timedelta(seconds=6, microseconds=328199), datetime.timedelta(seconds=6, microseconds=290364)]
Phi time: [datetime.timedelta(seconds=5, microseconds=852222), datetime.timedelta(seconds=5, microseconds=789435), datetime.timedelta(seconds=5, microseconds=848190), datetime.timedelta(seconds=5, microseconds=857168), datetime.timedelta(seconds=5, microseconds=856152), datetime.timedelta(seconds=5, microseconds=864121), datetime.timedelta(seconds=5, microseconds=817315), datetime.timedelta(seconds=5, microseconds=839220), datetime.timedelta(seconds=5, microseconds=877057), datetime.timedelta(seconds=5, microseconds=831210)]
