Precision: [tensor(0.8198, device='cuda:0'), tensor(0.8194, device='cuda:0'), tensor(0.8183, device='cuda:0'), tensor(0.8199, device='cuda:0'), tensor(0.8192, device='cuda:0'), tensor(0.8188, device='cuda:0'), tensor(0.8201, device='cuda:0'), tensor(0.8186, device='cuda:0'), tensor(0.8198, device='cuda:0'), tensor(0.8201, device='cuda:0')]

Output distance: [tensor(14626.7197, device='cuda:0'), tensor(16101.0117, device='cuda:0'), tensor(14737.4141, device='cuda:0'), tensor(14446.1104, device='cuda:0'), tensor(14375.2568, device='cuda:0'), tensor(15023.7881, device='cuda:0'), tensor(14535.4785, device='cuda:0'), tensor(14908.1318, device='cuda:0'), tensor(14455.8281, device='cuda:0'), tensor(14523.8867, device='cuda:0')]

Prediction loss: [tensor(11209.7520, device='cuda:0'), tensor(12785.1172, device='cuda:0'), tensor(10903.8955, device='cuda:0'), tensor(10565.8682, device='cuda:0'), tensor(10681.6797, device='cuda:0'), tensor(11189.7383, device='cuda:0'), tensor(11096.9609, device='cuda:0'), tensor(11205.4785, device='cuda:0'), tensor(10767.3525, device='cuda:0'), tensor(10908.0410, device='cuda:0')]

Others: [{'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(17997, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(1.9147e+08, device='cuda:0'), tensor(1.8969e+08, device='cuda:0'), tensor(1.9152e+08, device='cuda:0'), tensor(1.8839e+08, device='cuda:0'), tensor(1.9087e+08, device='cuda:0'), tensor(1.9270e+08, device='cuda:0'), tensor(1.9053e+08, device='cuda:0'), tensor(1.9262e+08, device='cuda:0'), tensor(1.9055e+08, device='cuda:0'), tensor(1.9128e+08, device='cuda:0')]

Training loss: 191074080.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=634070), datetime.timedelta(seconds=1, microseconds=693814), datetime.timedelta(seconds=1, microseconds=675893), datetime.timedelta(seconds=1, microseconds=696863), datetime.timedelta(seconds=1, microseconds=681925), datetime.timedelta(seconds=1, microseconds=677943), datetime.timedelta(seconds=1, microseconds=656956), datetime.timedelta(seconds=1, microseconds=665988), datetime.timedelta(seconds=1, microseconds=667983), datetime.timedelta(seconds=1, microseconds=665993)]

Phi time: [datetime.timedelta(seconds=1, microseconds=432517), datetime.timedelta(microseconds=868778), datetime.timedelta(microseconds=795651), datetime.timedelta(microseconds=800138), datetime.timedelta(microseconds=804241), datetime.timedelta(microseconds=792018), datetime.timedelta(microseconds=798050), datetime.timedelta(microseconds=799368), datetime.timedelta(microseconds=802087), datetime.timedelta(microseconds=801899)]

