Precision: [tensor(0.5583, device='cuda:0'), tensor(0.5405, device='cuda:0'), tensor(0.5227, device='cuda:0'), tensor(0.5455, device='cuda:0'), tensor(0.5363, device='cuda:0'), tensor(0.5283, device='cuda:0'), tensor(0.5382, device='cuda:0'), tensor(0.5333, device='cuda:0'), tensor(0.5547, device='cuda:0'), tensor(0.5482, device='cuda:0')]
Output distance: [tensor(18.9087, device='cuda:0'), tensor(18.9444, device='cuda:0'), tensor(18.9800, device='cuda:0'), tensor(18.9344, device='cuda:0'), tensor(18.9528, device='cuda:0'), tensor(18.9689, device='cuda:0'), tensor(18.9489, device='cuda:0'), tensor(18.9589, device='cuda:0'), tensor(18.9160, device='cuda:0'), tensor(18.9290, device='cuda:0')]
Prediction loss: [tensor(109.5931, device='cuda:0'), tensor(108.7787, device='cuda:0'), tensor(109.4306, device='cuda:0'), tensor(108.3121, device='cuda:0'), tensor(108.6260, device='cuda:0'), tensor(108.5756, device='cuda:0'), tensor(108.4778, device='cuda:0'), tensor(108.9557, device='cuda:0'), tensor(108.5326, device='cuda:0'), tensor(108.4224, 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=10, microseconds=866573), datetime.timedelta(seconds=10, microseconds=886354), datetime.timedelta(seconds=10, microseconds=916703), datetime.timedelta(seconds=10, microseconds=750425), datetime.timedelta(seconds=10, microseconds=749155), datetime.timedelta(seconds=10, microseconds=866509), datetime.timedelta(seconds=10, microseconds=783107), datetime.timedelta(seconds=10, microseconds=766421), datetime.timedelta(seconds=10, microseconds=799807), datetime.timedelta(seconds=10, microseconds=767752)]
Phi time: [datetime.timedelta(seconds=111, microseconds=521428), datetime.timedelta(seconds=99, microseconds=515888), datetime.timedelta(seconds=99, microseconds=344764), datetime.timedelta(seconds=99, microseconds=336898), datetime.timedelta(seconds=99, microseconds=567437), datetime.timedelta(seconds=99, microseconds=440723), datetime.timedelta(seconds=99, microseconds=516238), datetime.timedelta(seconds=99, microseconds=316364), datetime.timedelta(seconds=99, microseconds=399613), datetime.timedelta(seconds=99, microseconds=456092)]
