Precision: [tensor(0.6369, device='cuda:0'), tensor(0.6437, device='cuda:0'), tensor(0.6388, device='cuda:0'), tensor(0.6490, device='cuda:0'), tensor(0.6348, device='cuda:0'), tensor(0.6430, device='cuda:0'), tensor(0.6411, device='cuda:0'), tensor(0.6385, device='cuda:0'), tensor(0.6330, device='cuda:0'), tensor(0.6435, device='cuda:0')]

Output distance: [tensor(5.0323, device='cuda:0'), tensor(5.0186, device='cuda:0'), tensor(5.0286, device='cuda:0'), tensor(5.0081, device='cuda:0'), tensor(5.0365, device='cuda:0'), tensor(5.0202, device='cuda:0'), tensor(5.0239, device='cuda:0'), tensor(5.0291, device='cuda:0'), tensor(5.0402, device='cuda:0'), tensor(5.0192, device='cuda:0')]

Prediction loss: [tensor(18689514., device='cuda:0'), tensor(19006720., device='cuda:0'), tensor(17515790., device='cuda:0'), tensor(17083996., device='cuda:0'), tensor(18118722., device='cuda:0'), tensor(18918400., device='cuda:0'), tensor(20714150., device='cuda:0'), tensor(19579180., device='cuda:0'), tensor(18224534., device='cuda:0'), tensor(15819897., device='cuda:0')]

Others: [{'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 30, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 5, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 9, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}, {'iter_num': 7, 'num_positive': tensor(3809, device='cuda:0'), 'num_positive_true': tensor(20211, device='cuda:0')}]

Compressed training loss: [tensor(40783.0938, device='cuda:0'), tensor(41095.0469, device='cuda:0'), tensor(41002., device='cuda:0'), tensor(40821.0039, device='cuda:0'), tensor(40783.9297, device='cuda:0'), tensor(40921.4766, device='cuda:0'), tensor(40891.1094, device='cuda:0'), tensor(40588.9375, device='cuda:0'), tensor(40999.6328, device='cuda:0'), tensor(40420.2070, device='cuda:0')]

Training loss: 0

Prediction time: [datetime.timedelta(microseconds=970066), datetime.timedelta(seconds=1, microseconds=2443), datetime.timedelta(microseconds=973412), datetime.timedelta(seconds=1, microseconds=100221), datetime.timedelta(microseconds=949057), datetime.timedelta(seconds=1, microseconds=52236), datetime.timedelta(microseconds=982278), datetime.timedelta(microseconds=972454), datetime.timedelta(microseconds=987277), datetime.timedelta(microseconds=964257)]

Phi time: [datetime.timedelta(microseconds=182312), datetime.timedelta(microseconds=180366), datetime.timedelta(microseconds=196516), datetime.timedelta(microseconds=169499), datetime.timedelta(microseconds=199771), datetime.timedelta(microseconds=196633), datetime.timedelta(microseconds=184319), datetime.timedelta(microseconds=180512), datetime.timedelta(microseconds=180660), datetime.timedelta(microseconds=193767)]

