Precision: [tensor(0.9995, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9997, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9993, device='cuda:0'), tensor(0.9995, device='cuda:0'), tensor(0.9998, device='cuda:0'), tensor(0.9998, device='cuda:0')]

Output distance: [tensor(23217.8633, device='cuda:0'), tensor(23274.9922, device='cuda:0'), tensor(23390.5469, device='cuda:0'), tensor(23298.0137, device='cuda:0'), tensor(23287.6699, device='cuda:0'), tensor(23250.5215, device='cuda:0'), tensor(23366.8477, device='cuda:0'), tensor(23259.0137, device='cuda:0'), tensor(23278.8848, device='cuda:0'), tensor(23276.1250, device='cuda:0')]

Prediction loss: [tensor(23231.7578, device='cuda:0'), tensor(23285.1270, device='cuda:0'), tensor(22402.4316, device='cuda:0'), tensor(24445.0898, device='cuda:0'), tensor(22635.7988, device='cuda:0'), tensor(24601.9062, device='cuda:0'), tensor(22979.5762, device='cuda:0'), tensor(22682.6562, device='cuda:0'), tensor(22816.6348, device='cuda:0'), tensor(22276.0273, device='cuda:0')]

Others: [{'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': 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')}, {'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(8834420., device='cuda:0'), tensor(8759100., device='cuda:0'), tensor(8693382., device='cuda:0'), tensor(9069615., device='cuda:0'), tensor(8819466., device='cuda:0'), tensor(9056566., device='cuda:0'), tensor(8865220., device='cuda:0'), tensor(8708619., device='cuda:0'), tensor(8817700., device='cuda:0'), tensor(8729966., device='cuda:0')]

Training loss: 8823645.0

Prediction time: [datetime.timedelta(microseconds=656217), datetime.timedelta(microseconds=778698), datetime.timedelta(microseconds=766749), datetime.timedelta(microseconds=681111), datetime.timedelta(microseconds=711980), datetime.timedelta(microseconds=680118), datetime.timedelta(microseconds=675136), datetime.timedelta(microseconds=680131), datetime.timedelta(microseconds=670158), datetime.timedelta(microseconds=765755)]

Phi time: [datetime.timedelta(seconds=1, microseconds=487926), datetime.timedelta(microseconds=912141), datetime.timedelta(microseconds=858267), datetime.timedelta(microseconds=859157), datetime.timedelta(microseconds=880086), datetime.timedelta(microseconds=853609), datetime.timedelta(microseconds=878032), datetime.timedelta(microseconds=864540), datetime.timedelta(microseconds=891313), datetime.timedelta(microseconds=860608)]

