Special test with strict convergence condition

Precision: [tensor(0.2822, device='cuda:0'), tensor(0.2868, device='cuda:0'), tensor(0.2821, device='cuda:0'), tensor(0.2888, device='cuda:0'), tensor(0.2841, device='cuda:0'), tensor(0.2867, device='cuda:0'), tensor(0.2857, device='cuda:0'), tensor(0.2835, device='cuda:0'), tensor(0.2824, device='cuda:0'), tensor(0.2842, device='cuda:0')]

Output distance: [tensor(6.6128, device='cuda:0'), tensor(6.5855, device='cuda:0'), tensor(6.6138, device='cuda:0'), tensor(6.5734, device='cuda:0'), tensor(6.6017, device='cuda:0'), tensor(6.5860, device='cuda:0'), tensor(6.5918, device='cuda:0'), tensor(6.6054, device='cuda:0'), tensor(6.6117, device='cuda:0'), tensor(6.6007, device='cuda:0')]

Prediction loss: [tensor(19294088., device='cuda:0'), tensor(18147370., device='cuda:0'), tensor(18577252., device='cuda:0'), tensor(18268584., device='cuda:0'), tensor(18752696., device='cuda:0'), tensor(18053342., device='cuda:0'), tensor(18721638., device='cuda:0'), tensor(17768058., device='cuda:0'), tensor(19150358., device='cuda:0'), tensor(18227414., device='cuda:0')]

Others: [{'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(11427, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40765.9844, device='cuda:0'), tensor(41100.1211, device='cuda:0'), tensor(40886.2031, device='cuda:0'), tensor(40913.1289, device='cuda:0'), tensor(40802.0508, device='cuda:0'), tensor(41032.5234, device='cuda:0'), tensor(40895.5156, device='cuda:0'), tensor(40851.2539, device='cuda:0'), tensor(40822.7812, device='cuda:0'), tensor(40881.0547, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(seconds=1, microseconds=93363), datetime.timedelta(seconds=1, microseconds=101328), datetime.timedelta(seconds=1, microseconds=77430), datetime.timedelta(seconds=1, microseconds=75439), datetime.timedelta(seconds=1, microseconds=86392), datetime.timedelta(seconds=1, microseconds=102325), datetime.timedelta(seconds=1, microseconds=84401), datetime.timedelta(seconds=1, microseconds=75440), datetime.timedelta(seconds=1, microseconds=87388), datetime.timedelta(seconds=1, microseconds=76434)]

Phi time: [datetime.timedelta(microseconds=238987), datetime.timedelta(microseconds=259898), datetime.timedelta(microseconds=232016), datetime.timedelta(microseconds=235999), datetime.timedelta(microseconds=236995), datetime.timedelta(microseconds=253924), datetime.timedelta(microseconds=236994), datetime.timedelta(microseconds=236995), datetime.timedelta(microseconds=251932), datetime.timedelta(microseconds=235005)]

