Precision: [tensor(0.9586, device='cuda:0'), tensor(0.9628, device='cuda:0'), tensor(0.9591, device='cuda:0'), tensor(0.9584, device='cuda:0'), tensor(0.9595, device='cuda:0'), tensor(0.9558, device='cuda:0'), tensor(0.9630, device='cuda:0'), tensor(0.9616, device='cuda:0'), tensor(0.9619, device='cuda:0'), tensor(0.9583, device='cuda:0')]

Output distance: [tensor(108.2721, device='cuda:0'), tensor(102.1545, device='cuda:0'), tensor(110.9915, device='cuda:0'), tensor(110.2437, device='cuda:0'), tensor(100.8331, device='cuda:0'), tensor(113.2712, device='cuda:0'), tensor(100.5132, device='cuda:0'), tensor(102.8969, device='cuda:0'), tensor(105.9583, device='cuda:0'), tensor(112.7078, device='cuda:0')]

Prediction loss: [tensor(369.0067, device='cuda:0'), tensor(368.9500, device='cuda:0'), tensor(390.6823, device='cuda:0'), tensor(376.3912, device='cuda:0'), tensor(360.5110, device='cuda:0'), tensor(390.6969, device='cuda:0'), tensor(347.1180, device='cuda:0'), tensor(384.0194, device='cuda:0'), tensor(345.0981, device='cuda:0'), tensor(362.8627, device='cuda:0')]

Others: [{'iter_num': 13, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 15, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 15, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 13, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 17, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 15, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 15, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 15, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(3555053.2500, device='cuda:0'), tensor(3521253.2500, device='cuda:0'), tensor(3762872.5000, device='cuda:0'), tensor(3616663.7500, device='cuda:0'), tensor(3431954.7500, device='cuda:0'), tensor(3756642.7500, device='cuda:0'), tensor(3329878.2500, device='cuda:0'), tensor(3668592.2500, device='cuda:0'), tensor(3314310.5000, device='cuda:0'), tensor(3480659.5000, device='cuda:0')]

Training loss: 3593242.0

Prediction time: [datetime.timedelta(microseconds=726918), datetime.timedelta(microseconds=811566), datetime.timedelta(microseconds=767744), datetime.timedelta(microseconds=815542), datetime.timedelta(microseconds=749820), datetime.timedelta(microseconds=747829), datetime.timedelta(microseconds=882259), datetime.timedelta(microseconds=821516), datetime.timedelta(microseconds=810566), datetime.timedelta(microseconds=818529)]

Phi time: [datetime.timedelta(seconds=1, microseconds=323540), datetime.timedelta(microseconds=815219), datetime.timedelta(microseconds=739592), datetime.timedelta(microseconds=739994), datetime.timedelta(microseconds=752854), datetime.timedelta(microseconds=742619), datetime.timedelta(microseconds=771108), datetime.timedelta(microseconds=742565), datetime.timedelta(microseconds=741609), datetime.timedelta(microseconds=742896)]

