Precision: [tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9995, device='cuda:0')]

Output distance: [tensor(23413.9355, device='cuda:0'), tensor(23305.2070, device='cuda:0'), tensor(23303.5723, device='cuda:0'), tensor(23387.0391, device='cuda:0'), tensor(23394.9707, device='cuda:0'), tensor(23314.3730, device='cuda:0'), tensor(23268.2871, device='cuda:0'), tensor(23197.8672, device='cuda:0'), tensor(23446.3125, device='cuda:0'), tensor(23475.9375, device='cuda:0')]

Prediction loss: [tensor(23047.5273, device='cuda:0'), tensor(24163.4883, device='cuda:0'), tensor(21691.1426, device='cuda:0'), tensor(21978.4629, device='cuda:0'), tensor(23386.8496, device='cuda:0'), tensor(23621.2207, device='cuda:0'), tensor(23009.2930, device='cuda:0'), tensor(22484.1250, device='cuda:0'), tensor(23983.4883, device='cuda:0'), tensor(23329.4766, device='cuda:0')]

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

Compressed training loss: [tensor(8825641., device='cuda:0'), tensor(8923859., device='cuda:0'), tensor(8634356., device='cuda:0'), tensor(8620214., device='cuda:0'), tensor(8704622., device='cuda:0'), tensor(8953895., device='cuda:0'), tensor(8928493., device='cuda:0'), tensor(8777263., device='cuda:0'), tensor(9035230., device='cuda:0'), tensor(9005714., device='cuda:0')]

Training loss: 8882055.0

Prediction time: [datetime.timedelta(microseconds=630327), datetime.timedelta(microseconds=602444), datetime.timedelta(microseconds=649250), datetime.timedelta(microseconds=654225), datetime.timedelta(microseconds=644268), datetime.timedelta(microseconds=592489), datetime.timedelta(microseconds=649246), datetime.timedelta(microseconds=658213), datetime.timedelta(microseconds=589501), datetime.timedelta(microseconds=652233)]

Phi time: [datetime.timedelta(seconds=1, microseconds=391353), datetime.timedelta(microseconds=849461), datetime.timedelta(microseconds=789134), datetime.timedelta(microseconds=793195), datetime.timedelta(microseconds=785683), datetime.timedelta(microseconds=786882), datetime.timedelta(microseconds=792062), datetime.timedelta(microseconds=795207), datetime.timedelta(microseconds=787373), datetime.timedelta(microseconds=797405)]

