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

Output distance: [tensor(25408.8027, device='cuda:0'), tensor(23690.4238, device='cuda:0'), tensor(23786.5508, device='cuda:0'), tensor(24251.6699, device='cuda:0'), tensor(23933.3281, device='cuda:0'), tensor(24076.3926, device='cuda:0'), tensor(23698.5312, device='cuda:0'), tensor(23599.7305, device='cuda:0'), tensor(23923.7168, device='cuda:0'), tensor(23967.0684, device='cuda:0')]

Prediction loss: [tensor(26389.0586, device='cuda:0'), tensor(23960.8164, device='cuda:0'), tensor(23240.8379, device='cuda:0'), tensor(24279.8965, device='cuda:0'), tensor(24093.4336, device='cuda:0'), tensor(24025.8535, device='cuda:0'), tensor(22610.4434, device='cuda:0'), tensor(23997.9473, device='cuda:0'), tensor(23706.7734, device='cuda:0'), tensor(23625.3359, device='cuda:0')]

Others: [{'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 17, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 21, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 25, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 23, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 15, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(6000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(8992316., device='cuda:0'), tensor(8822078., device='cuda:0'), tensor(8702635., device='cuda:0'), tensor(8829532., device='cuda:0'), tensor(8839622., device='cuda:0'), tensor(8901386., device='cuda:0'), tensor(8697924., device='cuda:0'), tensor(8815076., device='cuda:0'), tensor(8886584., device='cuda:0'), tensor(8861478., device='cuda:0')]

Training loss: 8854709.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=881023), datetime.timedelta(seconds=1, microseconds=249700), datetime.timedelta(seconds=1, microseconds=436906), datetime.timedelta(seconds=1, microseconds=648011), datetime.timedelta(seconds=1, microseconds=900940), datetime.timedelta(seconds=1, microseconds=538465), datetime.timedelta(seconds=1, microseconds=103319), datetime.timedelta(microseconds=697043), datetime.timedelta(seconds=1, microseconds=914881), datetime.timedelta(seconds=1, microseconds=910895)]

Phi time: [datetime.timedelta(seconds=1, microseconds=561870), datetime.timedelta(microseconds=985855), datetime.timedelta(microseconds=955272), datetime.timedelta(microseconds=951838), datetime.timedelta(microseconds=955615), datetime.timedelta(microseconds=951714), datetime.timedelta(microseconds=955363), datetime.timedelta(microseconds=957168), datetime.timedelta(microseconds=955037), datetime.timedelta(microseconds=948138)]

