Precision: [tensor(0.4552, device='cuda:0'), tensor(0.4546, device='cuda:0'), tensor(0.4568, device='cuda:0'), tensor(0.4470, device='cuda:0'), tensor(0.4530, device='cuda:0'), tensor(0.4519, device='cuda:0'), tensor(0.4588, device='cuda:0'), tensor(0.4581, device='cuda:0'), tensor(0.4516, device='cuda:0'), tensor(0.4568, device='cuda:0')]
Output distance: [tensor(19.2530, device='cuda:0'), tensor(19.2567, device='cuda:0'), tensor(19.2456, device='cuda:0'), tensor(19.2946, device='cuda:0'), tensor(19.2648, device='cuda:0'), tensor(19.2697, device='cuda:0'), tensor(19.2349, device='cuda:0'), tensor(19.2390, device='cuda:0'), tensor(19.2713, device='cuda:0'), tensor(19.2458, device='cuda:0')]
Prediction loss: [tensor(103.8108, device='cuda:0'), tensor(104.5353, device='cuda:0'), tensor(105.3528, device='cuda:0'), tensor(104.3787, device='cuda:0'), tensor(104.4895, device='cuda:0'), tensor(104.4206, device='cuda:0'), tensor(104.8336, device='cuda:0'), tensor(104.7808, device='cuda:0'), tensor(104.2574, device='cuda:0'), tensor(104.5823, device='cuda:0')]
Others: [{'iter_num': 9, 'num_positive': tensor(16812, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16846, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16877, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16813, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16850, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16802, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16820, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(16843, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(16797, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(16884, 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=865829), datetime.timedelta(seconds=2, microseconds=883054), datetime.timedelta(seconds=2, microseconds=866648), datetime.timedelta(seconds=2, microseconds=866494), datetime.timedelta(seconds=2, microseconds=899647), datetime.timedelta(seconds=2, microseconds=866615), datetime.timedelta(seconds=2, microseconds=866374), datetime.timedelta(seconds=2, microseconds=733225), datetime.timedelta(seconds=2, microseconds=749765), datetime.timedelta(seconds=2, microseconds=866354)]
Phi time: [datetime.timedelta(seconds=99, microseconds=681073), datetime.timedelta(seconds=99, microseconds=518631), datetime.timedelta(seconds=99, microseconds=485363), datetime.timedelta(seconds=99, microseconds=518584), datetime.timedelta(seconds=99, microseconds=349687), datetime.timedelta(seconds=99, microseconds=282528), datetime.timedelta(seconds=99, microseconds=482916), datetime.timedelta(seconds=99, microseconds=433505), datetime.timedelta(seconds=99, microseconds=432278), datetime.timedelta(seconds=99, microseconds=500416)]
