Precision: [tensor(0.9997, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0')]

Output distance: [tensor(23270.1387, device='cuda:0'), tensor(23175.6660, device='cuda:0'), tensor(23185.3828, device='cuda:0'), tensor(23256.0293, device='cuda:0'), tensor(23155.3926, device='cuda:0'), tensor(23242.0527, device='cuda:0'), tensor(23273.6523, device='cuda:0'), tensor(23141.8164, device='cuda:0'), tensor(23203.1758, device='cuda:0'), tensor(23149.2793, device='cuda:0')]

Prediction loss: [tensor(23674.6191, device='cuda:0'), tensor(22158.4297, device='cuda:0'), tensor(23156.5254, device='cuda:0'), tensor(22765.4668, device='cuda:0'), tensor(22771.5059, device='cuda:0'), tensor(22638.2930, device='cuda:0'), tensor(24192.4336, device='cuda:0'), tensor(23370.0586, device='cuda:0'), tensor(22820.2578, device='cuda:0'), tensor(23740.8164, device='cuda:0')]

Others: [{'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 11, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(8947176., device='cuda:0'), tensor(8720267., device='cuda:0'), tensor(8781832., device='cuda:0'), tensor(8807840., device='cuda:0'), tensor(8764709., device='cuda:0'), tensor(8650130., device='cuda:0'), tensor(9008256., device='cuda:0'), tensor(8810910., device='cuda:0'), tensor(8803480., device='cuda:0'), tensor(8979514., device='cuda:0')]

Training loss: 8850180.0

Prediction time: [datetime.timedelta(microseconds=772721), datetime.timedelta(microseconds=819525), datetime.timedelta(microseconds=708994), datetime.timedelta(microseconds=704014), datetime.timedelta(microseconds=717955), datetime.timedelta(microseconds=809568), datetime.timedelta(microseconds=701027), datetime.timedelta(microseconds=719946), datetime.timedelta(microseconds=710936), datetime.timedelta(microseconds=712976)]

Phi time: [datetime.timedelta(seconds=1, microseconds=558713), datetime.timedelta(microseconds=988100), datetime.timedelta(microseconds=955646), datetime.timedelta(microseconds=952613), datetime.timedelta(microseconds=996659), datetime.timedelta(microseconds=951158), datetime.timedelta(microseconds=952238), datetime.timedelta(microseconds=953144), datetime.timedelta(microseconds=955777), datetime.timedelta(microseconds=949649)]

