Precision: [tensor(0.8278, device='cuda:0'), tensor(0.8246, device='cuda:0'), tensor(0.8278, device='cuda:0'), tensor(0.8284, device='cuda:0'), tensor(0.8269, device='cuda:0'), tensor(0.8262, device='cuda:0'), tensor(0.8269, device='cuda:0'), tensor(0.8272, device='cuda:0'), tensor(0.8272, device='cuda:0'), tensor(0.8271, device='cuda:0')]

Output distance: [tensor(13562.1016, device='cuda:0'), tensor(13772.8682, device='cuda:0'), tensor(13557.8760, device='cuda:0'), tensor(13505.8301, device='cuda:0'), tensor(13630.9746, device='cuda:0'), tensor(13682.0693, device='cuda:0'), tensor(13604.4131, device='cuda:0'), tensor(13597.1348, device='cuda:0'), tensor(13600.0635, device='cuda:0'), tensor(13574.0264, device='cuda:0')]

Prediction loss: [tensor(10390.0908, device='cuda:0'), tensor(10294.5762, device='cuda:0'), tensor(10368.0615, device='cuda:0'), tensor(10301.4219, device='cuda:0'), tensor(10401.6855, device='cuda:0'), tensor(10535.3516, device='cuda:0'), tensor(10559.8223, device='cuda:0'), tensor(10328.8740, device='cuda:0'), tensor(10429.5635, device='cuda:0'), tensor(10328.2139, device='cuda:0')]

Others: [{'iter_num': 13, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, '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': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, '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': 11, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(1.9288e+08, device='cuda:0'), tensor(1.9050e+08, device='cuda:0'), tensor(1.9170e+08, device='cuda:0'), tensor(1.9117e+08, device='cuda:0'), tensor(1.9266e+08, device='cuda:0'), tensor(1.9532e+08, device='cuda:0'), tensor(1.9543e+08, device='cuda:0'), tensor(1.9198e+08, device='cuda:0'), tensor(1.9400e+08, device='cuda:0'), tensor(1.9138e+08, device='cuda:0')]

Training loss: 192609680.0

Prediction time: [datetime.timedelta(microseconds=817536), datetime.timedelta(microseconds=794630), datetime.timedelta(microseconds=832472), datetime.timedelta(microseconds=849398), datetime.timedelta(microseconds=748876), datetime.timedelta(microseconds=756790), datetime.timedelta(microseconds=750814), datetime.timedelta(microseconds=749817), datetime.timedelta(microseconds=861347), datetime.timedelta(microseconds=741800)]

Phi time: [datetime.timedelta(seconds=1, microseconds=398625), datetime.timedelta(microseconds=894633), datetime.timedelta(microseconds=856958), datetime.timedelta(microseconds=852883), datetime.timedelta(microseconds=853100), datetime.timedelta(microseconds=877209), datetime.timedelta(microseconds=859317), datetime.timedelta(microseconds=849197), datetime.timedelta(microseconds=853651), datetime.timedelta(microseconds=858824)]

