Precision: [tensor(0.5346, device='cuda:0'), tensor(0.5388, device='cuda:0'), tensor(0.5496, device='cuda:0'), tensor(0.5481, device='cuda:0'), tensor(0.5293, device='cuda:0'), tensor(0.5565, device='cuda:0'), tensor(0.5322, device='cuda:0'), tensor(0.5333, device='cuda:0'), tensor(0.5597, device='cuda:0'), tensor(0.5537, device='cuda:0')]
Output distance: [tensor(18.9562, device='cuda:0'), tensor(18.9477, device='cuda:0'), tensor(18.9262, device='cuda:0'), tensor(18.9293, device='cuda:0'), tensor(18.9667, device='cuda:0'), tensor(18.9123, device='cuda:0'), tensor(18.9610, device='cuda:0'), tensor(18.9589, device='cuda:0'), tensor(18.9060, device='cuda:0'), tensor(18.9181, device='cuda:0')]
Prediction loss: [tensor(108.6855, device='cuda:0'), tensor(108.6574, device='cuda:0'), tensor(108.3575, device='cuda:0'), tensor(108.9810, device='cuda:0'), tensor(108.7022, device='cuda:0'), tensor(109.6367, device='cuda:0'), tensor(108.8054, device='cuda:0'), tensor(108.9944, device='cuda:0'), tensor(108.5879, device='cuda:0'), tensor(109.3909, device='cuda:0')]
Others: [{'iter_num': 30, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6616, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, '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=4, microseconds=344302), datetime.timedelta(seconds=4, microseconds=328662), datetime.timedelta(seconds=4, microseconds=292294), datetime.timedelta(seconds=4, microseconds=287031), datetime.timedelta(seconds=4, microseconds=288128), datetime.timedelta(seconds=4, microseconds=296450), datetime.timedelta(seconds=4, microseconds=269724), datetime.timedelta(seconds=4, microseconds=295684), datetime.timedelta(seconds=4, microseconds=287561), datetime.timedelta(seconds=4, microseconds=267180)]
Phi time: [datetime.timedelta(seconds=97, microseconds=497835), datetime.timedelta(seconds=97, microseconds=414577), datetime.timedelta(seconds=97, microseconds=408317), datetime.timedelta(seconds=97, microseconds=287416), datetime.timedelta(seconds=97, microseconds=111407), datetime.timedelta(seconds=97, microseconds=349915), datetime.timedelta(seconds=97, microseconds=325165), datetime.timedelta(seconds=97, microseconds=402564), datetime.timedelta(seconds=97, microseconds=415967), datetime.timedelta(seconds=97, microseconds=403002)]
