Special test with strict convergence condition

Precision: [tensor(0.6884, device='cuda:0'), tensor(0.6868, device='cuda:0'), tensor(0.6907, device='cuda:0'), tensor(0.6821, device='cuda:0'), tensor(0.6852, device='cuda:0'), tensor(0.6889, device='cuda:0'), tensor(0.6844, device='cuda:0'), tensor(0.6897, device='cuda:0'), tensor(0.6884, device='cuda:0'), tensor(0.6913, device='cuda:0')]

Output distance: [tensor(4.9294, device='cuda:0'), tensor(4.9325, device='cuda:0'), tensor(4.9247, device='cuda:0'), tensor(4.9420, device='cuda:0'), tensor(4.9357, device='cuda:0'), tensor(4.9283, device='cuda:0'), tensor(4.9373, device='cuda:0'), tensor(4.9268, device='cuda:0'), tensor(4.9294, device='cuda:0'), tensor(4.9236, device='cuda:0')]

Prediction loss: [tensor(17928880., device='cuda:0'), tensor(18574190., device='cuda:0'), tensor(16936744., device='cuda:0'), tensor(18997142., device='cuda:0'), tensor(18501140., device='cuda:0'), tensor(17845970., device='cuda:0'), tensor(18563956., device='cuda:0'), tensor(19571898., device='cuda:0'), tensor(19550780., device='cuda:0'), tensor(18375138., device='cuda:0')]

Others: [{'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40937.0820, device='cuda:0'), tensor(40662.6875, device='cuda:0'), tensor(40649.9844, device='cuda:0'), tensor(40881.2773, device='cuda:0'), tensor(40895.8398, device='cuda:0'), tensor(40734.3164, device='cuda:0'), tensor(40782.7148, device='cuda:0'), tensor(40883.4609, device='cuda:0'), tensor(40890.4102, device='cuda:0'), tensor(40887.2578, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=21710), datetime.timedelta(seconds=1, microseconds=17726), datetime.timedelta(seconds=1, microseconds=36647), datetime.timedelta(seconds=1, microseconds=7769), datetime.timedelta(seconds=1, microseconds=22706), datetime.timedelta(seconds=1, microseconds=4782), datetime.timedelta(seconds=1, microseconds=33661), datetime.timedelta(seconds=1, microseconds=15735), datetime.timedelta(seconds=1, microseconds=33660), datetime.timedelta(microseconds=991837)]

Phi time: [datetime.timedelta(microseconds=394345), datetime.timedelta(microseconds=240988), datetime.timedelta(microseconds=236009), datetime.timedelta(microseconds=255926), datetime.timedelta(microseconds=233022), datetime.timedelta(microseconds=232026), datetime.timedelta(microseconds=236009), datetime.timedelta(microseconds=236009), datetime.timedelta(microseconds=241985), datetime.timedelta(microseconds=251942)]

