Precision: [tensor(0.3617, device='cuda:0'), tensor(0.3614, device='cuda:0'), tensor(0.3615, device='cuda:0'), tensor(0.3610, device='cuda:0'), tensor(0.3645, device='cuda:0'), tensor(0.3630, device='cuda:0'), tensor(0.3631, device='cuda:0'), tensor(0.3601, device='cuda:0'), tensor(0.3640, device='cuda:0'), tensor(0.3585, device='cuda:0')]
Output distance: [tensor(20.4081, device='cuda:0'), tensor(20.4117, device='cuda:0'), tensor(20.4108, device='cuda:0'), tensor(20.4154, device='cuda:0'), tensor(20.3803, device='cuda:0'), tensor(20.3954, device='cuda:0'), tensor(20.3939, device='cuda:0'), tensor(20.4241, device='cuda:0'), tensor(20.3857, device='cuda:0'), tensor(20.4401, device='cuda:0')]
Prediction loss: [tensor(101.3942, device='cuda:0'), tensor(101.6723, device='cuda:0'), tensor(101.5356, device='cuda:0'), tensor(102.1255, device='cuda:0'), tensor(101.5114, device='cuda:0'), tensor(101.3573, device='cuda:0'), tensor(101.8455, device='cuda:0'), tensor(101.0453, device='cuda:0'), tensor(102.8343, device='cuda:0'), tensor(101.0967, device='cuda:0')]
Others: [{'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, device='cuda:0'), 'num_positive_true': tensor(125872, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(33080, 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=516938), datetime.timedelta(seconds=4, microseconds=499903), datetime.timedelta(seconds=4, microseconds=500040), datetime.timedelta(seconds=4, microseconds=483416), datetime.timedelta(seconds=4, microseconds=500044), datetime.timedelta(seconds=4, microseconds=483499), datetime.timedelta(seconds=4, microseconds=516994), datetime.timedelta(seconds=4, microseconds=533445), datetime.timedelta(seconds=4, microseconds=516435), datetime.timedelta(seconds=4, microseconds=498754)]
Phi time: [datetime.timedelta(seconds=98, microseconds=781547), datetime.timedelta(seconds=99, microseconds=16185), datetime.timedelta(seconds=99, microseconds=49428), datetime.timedelta(seconds=98, microseconds=732775), datetime.timedelta(seconds=98, microseconds=718418), datetime.timedelta(seconds=98, microseconds=817140), datetime.timedelta(seconds=99, microseconds=2667), datetime.timedelta(seconds=99, microseconds=319494), datetime.timedelta(seconds=99, microseconds=250351), datetime.timedelta(seconds=98, microseconds=932785)]
