Precision: [tensor(0.8072, device='cuda:0'), tensor(0.8223, device='cuda:0'), tensor(0.8170, device='cuda:0'), tensor(0.8151, device='cuda:0'), tensor(0.8148, device='cuda:0'), tensor(0.8181, device='cuda:0'), tensor(0.8066, device='cuda:0'), tensor(0.8000, device='cuda:0'), tensor(0.8122, device='cuda:0'), tensor(0.8109, device='cuda:0')]

Output distance: [tensor(18494.3438, device='cuda:0'), tensor(14280.6758, device='cuda:0'), tensor(14615.3574, device='cuda:0'), tensor(14792.3867, device='cuda:0'), tensor(14815.7891, device='cuda:0'), tensor(14488.3281, device='cuda:0'), tensor(15029.1670, device='cuda:0'), tensor(18509.5859, device='cuda:0'), tensor(16693.7969, device='cuda:0'), tensor(14884.5723, device='cuda:0')]

Prediction loss: [tensor(17038.5098, device='cuda:0'), tensor(10646.8330, device='cuda:0'), tensor(10426.2695, device='cuda:0'), tensor(10888.0947, device='cuda:0'), tensor(10595.2734, device='cuda:0'), tensor(10340.8320, device='cuda:0'), tensor(9952.9814, device='cuda:0'), tensor(17168.4082, device='cuda:0'), tensor(14391.7656, device='cuda:0'), tensor(10430.7861, 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(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')}, {'iter_num': 30, 'num_positive': tensor(18000, device='cuda:0'), 'num_positive_true': tensor(18000, device='cuda:0')}]

Compressed training loss: [tensor(2.0021e+08, device='cuda:0'), tensor(1.9427e+08, device='cuda:0'), tensor(1.9319e+08, device='cuda:0'), tensor(1.9137e+08, device='cuda:0'), tensor(1.8575e+08, device='cuda:0'), tensor(1.9011e+08, device='cuda:0'), tensor(1.7878e+08, device='cuda:0'), tensor(1.9014e+08, device='cuda:0'), tensor(2.0353e+08, device='cuda:0'), tensor(1.8873e+08, device='cuda:0')]

Training loss: 191953888.0

Prediction time: [datetime.timedelta(seconds=1, microseconds=155101), datetime.timedelta(seconds=1, microseconds=187961), datetime.timedelta(seconds=1, microseconds=175017), datetime.timedelta(seconds=1, microseconds=183979), datetime.timedelta(seconds=1, microseconds=196925), datetime.timedelta(seconds=1, microseconds=191944), datetime.timedelta(seconds=1, microseconds=181987), datetime.timedelta(seconds=1, microseconds=192941), datetime.timedelta(seconds=1, microseconds=186965), datetime.timedelta(seconds=1, microseconds=179000)]

Phi time: [datetime.timedelta(seconds=1, microseconds=310021), datetime.timedelta(microseconds=740119), datetime.timedelta(microseconds=669147), datetime.timedelta(microseconds=671452), datetime.timedelta(microseconds=674186), datetime.timedelta(microseconds=671316), datetime.timedelta(microseconds=667533), datetime.timedelta(microseconds=666344), datetime.timedelta(microseconds=669642), datetime.timedelta(microseconds=671223)]

