==========
Args:Namespace(dataset='msmt17', batch_size=256, workers=4, height=256, width=128, num_instances=8, eps=0.7, eps_gap=0.02, k1=30, k2=6, arch='resnet101', pretrained_path='/home/ma-user/work/Projects/ReIDNets_Checkpoints_TransReID/ResNet101.pth', features=0, dropout=0, momentum=0.2, drop_path_rate=0.3, hw_ratio=2, self_norm=True, conv_stem=False, lr=0.00035, weight_decay=0.0005, optimizer='SGD', epochs=50, iters=200, step_size=20, seed=1, print_freq=20, eval_step=50, temp=0.05, data_dir='/home/ma-user/work/Projects/ReIDNet_Finetune/CContrast/data', logs_dir='log/msmt17/resnet101_cion', pooling_type='gem', use_hard=True)
==========
==> Load unlabeled dataset
=> MSMT17 loaded
Dataset statistics:
  ----------------------------------------
  subset   | # ids | # images | # cameras
  ----------------------------------------
  train    |  1041 |    32621 |        15
  query    |  3060 |    11659 |        15
  gallery  |  3060 |    82161 |        15
  ----------------------------------------
pooling_type: gem
optimizer: SGD
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.166 (0.375)	Data 0.000 (0.030)	
Extract Features: [100/128]	Time 0.185 (0.280)	Data 0.018 (0.022)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.035080909729004
Clustering criterion: eps: 0.700
==> Statistics for epoch 0: 887 clusters
Epoch: [0][20/200]	Time 0.518 (0.969)	Data 0.001 (0.050)	Loss 1.953 (2.422)
Epoch: [0][40/200]	Time 0.518 (0.788)	Data 0.001 (0.066)	Loss 3.334 (2.719)
Epoch: [0][60/200]	Time 0.521 (0.728)	Data 0.001 (0.071)	Loss 2.250 (2.844)
Epoch: [0][80/200]	Time 0.519 (0.676)	Data 0.000 (0.053)	Loss 2.476 (2.753)
Epoch: [0][100/200]	Time 0.522 (0.661)	Data 0.001 (0.059)	Loss 1.773 (2.650)
Epoch: [0][120/200]	Time 0.521 (0.651)	Data 0.001 (0.061)	Loss 1.637 (2.590)
Epoch: [0][140/200]	Time 0.536 (0.645)	Data 0.001 (0.064)	Loss 1.643 (2.528)
Epoch: [0][160/200]	Time 0.524 (0.630)	Data 0.000 (0.056)	Loss 2.195 (2.482)
Epoch: [0][180/200]	Time 0.522 (0.627)	Data 0.001 (0.059)	Loss 2.695 (2.428)
Epoch: [0][200/200]	Time 0.523 (0.625)	Data 0.001 (0.060)	Loss 1.511 (2.390)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.219)	Data 0.000 (0.046)	
Extract Features: [100/128]	Time 0.169 (0.201)	Data 0.000 (0.028)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.3309998512268
==> Statistics for epoch 1: 996 clusters
Epoch: [1][20/200]	Time 0.515 (0.573)	Data 0.000 (0.053)	Loss 0.361 (0.530)
Epoch: [1][40/200]	Time 0.524 (0.587)	Data 0.001 (0.066)	Loss 1.838 (0.899)
Epoch: [1][60/200]	Time 0.523 (0.569)	Data 0.000 (0.044)	Loss 1.811 (1.227)
Epoch: [1][80/200]	Time 0.523 (0.577)	Data 0.001 (0.053)	Loss 1.812 (1.406)
Epoch: [1][100/200]	Time 0.516 (0.583)	Data 0.001 (0.059)	Loss 1.480 (1.488)
Epoch: [1][120/200]	Time 0.521 (0.573)	Data 0.000 (0.049)	Loss 2.140 (1.556)
Epoch: [1][140/200]	Time 0.526 (0.579)	Data 0.001 (0.054)	Loss 2.126 (1.603)
Epoch: [1][160/200]	Time 0.521 (0.581)	Data 0.001 (0.057)	Loss 1.507 (1.625)
Epoch: [1][180/200]	Time 0.520 (0.574)	Data 0.000 (0.051)	Loss 2.164 (1.644)
Epoch: [1][200/200]	Time 0.523 (0.578)	Data 0.001 (0.053)	Loss 2.184 (1.658)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.317 (0.221)	Data 0.001 (0.048)	
Extract Features: [100/128]	Time 0.177 (0.200)	Data 0.000 (0.026)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.744778633117676
==> Statistics for epoch 2: 1017 clusters
Epoch: [2][20/200]	Time 0.518 (0.572)	Data 0.001 (0.052)	Loss 0.538 (0.774)
Epoch: [2][40/200]	Time 0.521 (0.592)	Data 0.001 (0.071)	Loss 1.968 (0.997)
Epoch: [2][60/200]	Time 0.515 (0.568)	Data 0.000 (0.048)	Loss 1.367 (1.284)
Epoch: [2][80/200]	Time 0.521 (0.578)	Data 0.001 (0.058)	Loss 1.691 (1.403)
Epoch: [2][100/200]	Time 0.521 (0.586)	Data 0.001 (0.064)	Loss 1.644 (1.467)
Epoch: [2][120/200]	Time 0.519 (0.575)	Data 0.000 (0.053)	Loss 1.722 (1.514)
Epoch: [2][140/200]	Time 0.519 (0.580)	Data 0.000 (0.057)	Loss 1.818 (1.535)
Epoch: [2][160/200]	Time 0.523 (0.583)	Data 0.000 (0.060)	Loss 1.307 (1.545)
Epoch: [2][180/200]	Time 0.520 (0.577)	Data 0.000 (0.054)	Loss 1.635 (1.567)
Epoch: [2][200/200]	Time 0.525 (0.580)	Data 0.001 (0.056)	Loss 1.438 (1.579)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.169 (0.217)	Data 0.000 (0.045)	
Extract Features: [100/128]	Time 0.171 (0.199)	Data 0.000 (0.027)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.23813009262085
==> Statistics for epoch 3: 1050 clusters
Epoch: [3][20/200]	Time 0.515 (0.569)	Data 0.001 (0.049)	Loss 0.564 (0.595)
Epoch: [3][40/200]	Time 0.518 (0.585)	Data 0.001 (0.066)	Loss 1.844 (0.831)
Epoch: [3][60/200]	Time 0.522 (0.563)	Data 0.000 (0.044)	Loss 1.711 (1.146)
Epoch: [3][80/200]	Time 0.522 (0.575)	Data 0.001 (0.054)	Loss 1.782 (1.302)
Epoch: [3][100/200]	Time 0.520 (0.582)	Data 0.001 (0.061)	Loss 1.670 (1.392)
Epoch: [3][120/200]	Time 0.521 (0.571)	Data 0.001 (0.051)	Loss 1.490 (1.443)
Epoch: [3][140/200]	Time 0.520 (0.578)	Data 0.001 (0.057)	Loss 1.918 (1.489)
Epoch: [3][160/200]	Time 0.520 (0.571)	Data 0.000 (0.050)	Loss 1.459 (1.515)
Epoch: [3][180/200]	Time 0.516 (0.576)	Data 0.001 (0.054)	Loss 1.722 (1.529)
Epoch: [3][200/200]	Time 0.522 (0.579)	Data 0.001 (0.057)	Loss 2.181 (1.543)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.173 (0.217)	Data 0.000 (0.042)	
Extract Features: [100/128]	Time 0.171 (0.198)	Data 0.000 (0.024)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.399792432785034
==> Statistics for epoch 4: 1041 clusters
Epoch: [4][20/200]	Time 0.518 (0.571)	Data 0.001 (0.052)	Loss 0.325 (0.504)
Epoch: [4][40/200]	Time 0.518 (0.590)	Data 0.001 (0.068)	Loss 1.967 (0.752)
Epoch: [4][60/200]	Time 0.519 (0.566)	Data 0.000 (0.046)	Loss 1.303 (1.090)
Epoch: [4][80/200]	Time 0.520 (0.575)	Data 0.001 (0.055)	Loss 2.088 (1.244)
Epoch: [4][100/200]	Time 0.529 (0.582)	Data 0.001 (0.061)	Loss 1.831 (1.346)
Epoch: [4][120/200]	Time 0.517 (0.573)	Data 0.001 (0.051)	Loss 1.214 (1.405)
Epoch: [4][140/200]	Time 0.518 (0.577)	Data 0.001 (0.056)	Loss 1.541 (1.447)
Epoch: [4][160/200]	Time 0.521 (0.571)	Data 0.000 (0.049)	Loss 1.772 (1.481)
Epoch: [4][180/200]	Time 0.520 (0.575)	Data 0.001 (0.053)	Loss 1.697 (1.507)
Epoch: [4][200/200]	Time 0.521 (0.579)	Data 0.001 (0.056)	Loss 1.551 (1.532)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.169 (0.217)	Data 0.000 (0.044)	
Extract Features: [100/128]	Time 0.175 (0.200)	Data 0.000 (0.026)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.84863805770874
==> Statistics for epoch 5: 1004 clusters
Epoch: [5][20/200]	Time 0.515 (0.569)	Data 0.001 (0.052)	Loss 0.349 (0.501)
Epoch: [5][40/200]	Time 0.524 (0.592)	Data 0.001 (0.070)	Loss 1.655 (0.719)
Epoch: [5][60/200]	Time 0.517 (0.570)	Data 0.000 (0.047)	Loss 1.474 (1.038)
Epoch: [5][80/200]	Time 0.520 (0.580)	Data 0.001 (0.058)	Loss 1.596 (1.166)
Epoch: [5][100/200]	Time 0.518 (0.586)	Data 0.001 (0.064)	Loss 1.232 (1.282)
Epoch: [5][120/200]	Time 0.518 (0.575)	Data 0.000 (0.053)	Loss 1.546 (1.337)
Epoch: [5][140/200]	Time 0.517 (0.580)	Data 0.001 (0.058)	Loss 1.917 (1.371)
Epoch: [5][160/200]	Time 0.520 (0.584)	Data 0.001 (0.062)	Loss 1.121 (1.403)
Epoch: [5][180/200]	Time 0.521 (0.578)	Data 0.000 (0.055)	Loss 1.701 (1.421)
Epoch: [5][200/200]	Time 0.521 (0.581)	Data 0.001 (0.058)	Loss 1.594 (1.435)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.168 (0.216)	Data 0.000 (0.044)	
Extract Features: [100/128]	Time 0.170 (0.199)	Data 0.000 (0.026)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.0575385093689
==> Statistics for epoch 6: 1049 clusters
Epoch: [6][20/200]	Time 0.516 (0.573)	Data 0.001 (0.056)	Loss 0.319 (0.422)
Epoch: [6][40/200]	Time 0.519 (0.587)	Data 0.001 (0.069)	Loss 1.270 (0.663)
Epoch: [6][60/200]	Time 0.521 (0.567)	Data 0.000 (0.046)	Loss 1.854 (1.028)
Epoch: [6][80/200]	Time 0.521 (0.580)	Data 0.001 (0.057)	Loss 1.603 (1.206)
Epoch: [6][100/200]	Time 0.524 (0.587)	Data 0.001 (0.064)	Loss 1.544 (1.302)
Epoch: [6][120/200]	Time 0.521 (0.576)	Data 0.001 (0.053)	Loss 1.678 (1.365)
Epoch: [6][140/200]	Time 0.518 (0.581)	Data 0.001 (0.058)	Loss 1.190 (1.409)
Epoch: [6][160/200]	Time 0.522 (0.574)	Data 0.000 (0.051)	Loss 1.573 (1.445)
Epoch: [6][180/200]	Time 0.523 (0.578)	Data 0.001 (0.054)	Loss 1.546 (1.465)
Epoch: [6][200/200]	Time 0.519 (0.581)	Data 0.001 (0.057)	Loss 1.719 (1.490)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.220)	Data 0.000 (0.046)	
Extract Features: [100/128]	Time 0.169 (0.202)	Data 0.000 (0.027)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.78765106201172
==> Statistics for epoch 7: 1027 clusters
Epoch: [7][20/200]	Time 0.516 (0.573)	Data 0.001 (0.055)	Loss 0.226 (0.394)
Epoch: [7][40/200]	Time 0.518 (0.587)	Data 0.001 (0.068)	Loss 1.369 (0.604)
Epoch: [7][60/200]	Time 0.517 (0.568)	Data 0.000 (0.046)	Loss 1.530 (0.981)
Epoch: [7][80/200]	Time 0.522 (0.579)	Data 0.001 (0.057)	Loss 1.520 (1.163)
Epoch: [7][100/200]	Time 0.520 (0.587)	Data 0.000 (0.064)	Loss 1.878 (1.280)
Epoch: [7][120/200]	Time 0.520 (0.576)	Data 0.001 (0.054)	Loss 2.344 (1.343)
Epoch: [7][140/200]	Time 0.518 (0.581)	Data 0.001 (0.058)	Loss 1.652 (1.398)
Epoch: [7][160/200]	Time 0.523 (0.574)	Data 0.000 (0.051)	Loss 1.562 (1.425)
Epoch: [7][180/200]	Time 0.519 (0.579)	Data 0.001 (0.056)	Loss 2.009 (1.459)
Epoch: [7][200/200]	Time 0.521 (0.582)	Data 0.001 (0.059)	Loss 1.825 (1.468)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.172 (0.219)	Data 0.000 (0.050)	
Extract Features: [100/128]	Time 0.172 (0.200)	Data 0.000 (0.029)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.76719427108765
==> Statistics for epoch 8: 1029 clusters
Epoch: [8][20/200]	Time 0.514 (0.576)	Data 0.000 (0.054)	Loss 0.417 (0.425)
Epoch: [8][40/200]	Time 0.515 (0.588)	Data 0.001 (0.068)	Loss 1.610 (0.668)
Epoch: [8][60/200]	Time 0.518 (0.566)	Data 0.000 (0.046)	Loss 1.382 (1.043)
Epoch: [8][80/200]	Time 0.519 (0.575)	Data 0.001 (0.055)	Loss 1.724 (1.200)
Epoch: [8][100/200]	Time 0.642 (0.582)	Data 0.001 (0.061)	Loss 1.477 (1.305)
Epoch: [8][120/200]	Time 0.519 (0.572)	Data 0.001 (0.051)	Loss 1.336 (1.371)
Epoch: [8][140/200]	Time 0.520 (0.577)	Data 0.001 (0.056)	Loss 1.283 (1.418)
Epoch: [8][160/200]	Time 0.518 (0.571)	Data 0.000 (0.049)	Loss 1.919 (1.449)
Epoch: [8][180/200]	Time 0.519 (0.574)	Data 0.001 (0.052)	Loss 1.619 (1.472)
Epoch: [8][200/200]	Time 0.521 (0.577)	Data 0.001 (0.055)	Loss 1.559 (1.493)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.168 (0.211)	Data 0.000 (0.037)	
Extract Features: [100/128]	Time 0.170 (0.195)	Data 0.000 (0.021)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.21440601348877
==> Statistics for epoch 9: 1034 clusters
Epoch: [9][20/200]	Time 0.517 (0.570)	Data 0.001 (0.052)	Loss 0.420 (0.531)
Epoch: [9][40/200]	Time 0.520 (0.593)	Data 0.001 (0.071)	Loss 1.384 (0.725)
Epoch: [9][60/200]	Time 0.517 (0.568)	Data 0.000 (0.048)	Loss 2.068 (1.055)
Epoch: [9][80/200]	Time 0.520 (0.578)	Data 0.001 (0.055)	Loss 1.844 (1.207)
Epoch: [9][100/200]	Time 0.523 (0.582)	Data 0.002 (0.060)	Loss 1.638 (1.277)
Epoch: [9][120/200]	Time 0.517 (0.572)	Data 0.001 (0.050)	Loss 1.534 (1.321)
Epoch: [9][140/200]	Time 0.521 (0.576)	Data 0.001 (0.054)	Loss 1.843 (1.353)
Epoch: [9][160/200]	Time 0.520 (0.570)	Data 0.000 (0.048)	Loss 1.425 (1.377)
Epoch: [9][180/200]	Time 0.524 (0.574)	Data 0.001 (0.052)	Loss 1.373 (1.383)
Epoch: [9][200/200]	Time 0.523 (0.578)	Data 0.000 (0.055)	Loss 1.164 (1.399)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.169 (0.215)	Data 0.000 (0.042)	
Extract Features: [100/128]	Time 0.171 (0.198)	Data 0.000 (0.025)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.47792410850525
==> Statistics for epoch 10: 1026 clusters
Epoch: [10][20/200]	Time 0.517 (0.571)	Data 0.001 (0.055)	Loss 0.413 (0.401)
Epoch: [10][40/200]	Time 0.524 (0.587)	Data 0.001 (0.070)	Loss 1.565 (0.632)
Epoch: [10][60/200]	Time 0.519 (0.564)	Data 0.000 (0.047)	Loss 1.358 (0.967)
Epoch: [10][80/200]	Time 0.519 (0.576)	Data 0.001 (0.058)	Loss 1.654 (1.124)
Epoch: [10][100/200]	Time 0.529 (0.582)	Data 0.001 (0.062)	Loss 1.611 (1.233)
Epoch: [10][120/200]	Time 0.522 (0.572)	Data 0.001 (0.052)	Loss 1.539 (1.286)
Epoch: [10][140/200]	Time 0.519 (0.577)	Data 0.001 (0.057)	Loss 1.241 (1.333)
Epoch: [10][160/200]	Time 0.518 (0.571)	Data 0.000 (0.050)	Loss 1.579 (1.356)
Epoch: [10][180/200]	Time 0.522 (0.575)	Data 0.001 (0.054)	Loss 1.343 (1.380)
Epoch: [10][200/200]	Time 0.519 (0.579)	Data 0.001 (0.058)	Loss 0.972 (1.393)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.169 (0.221)	Data 0.000 (0.046)	
Extract Features: [100/128]	Time 0.171 (0.200)	Data 0.000 (0.028)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.86294627189636
==> Statistics for epoch 11: 1042 clusters
Epoch: [11][20/200]	Time 0.514 (0.577)	Data 0.001 (0.052)	Loss 0.400 (0.339)
Epoch: [11][40/200]	Time 0.521 (0.588)	Data 0.001 (0.064)	Loss 1.814 (0.593)
Epoch: [11][60/200]	Time 0.518 (0.566)	Data 0.000 (0.043)	Loss 1.920 (0.930)
Epoch: [11][80/200]	Time 0.516 (0.576)	Data 0.001 (0.053)	Loss 1.704 (1.095)
Epoch: [11][100/200]	Time 0.529 (0.582)	Data 0.002 (0.059)	Loss 1.573 (1.212)
Epoch: [11][120/200]	Time 0.522 (0.573)	Data 0.001 (0.049)	Loss 1.443 (1.270)
Epoch: [11][140/200]	Time 0.522 (0.577)	Data 0.001 (0.054)	Loss 1.613 (1.321)
Epoch: [11][160/200]	Time 0.519 (0.570)	Data 0.000 (0.047)	Loss 1.917 (1.360)
Epoch: [11][180/200]	Time 0.520 (0.574)	Data 0.001 (0.051)	Loss 1.314 (1.388)
Epoch: [11][200/200]	Time 0.520 (0.576)	Data 0.001 (0.053)	Loss 1.597 (1.407)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.213)	Data 0.000 (0.041)	
Extract Features: [100/128]	Time 0.173 (0.200)	Data 0.000 (0.024)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.99001693725586
==> Statistics for epoch 12: 1032 clusters
Epoch: [12][20/200]	Time 0.519 (0.576)	Data 0.001 (0.052)	Loss 0.225 (0.360)
Epoch: [12][40/200]	Time 0.520 (0.591)	Data 0.001 (0.068)	Loss 1.466 (0.566)
Epoch: [12][60/200]	Time 0.518 (0.569)	Data 0.000 (0.046)	Loss 1.854 (0.897)
Epoch: [12][80/200]	Time 0.520 (0.579)	Data 0.002 (0.057)	Loss 1.778 (1.044)
Epoch: [12][100/200]	Time 0.520 (0.585)	Data 0.003 (0.063)	Loss 1.386 (1.134)
Epoch: [12][120/200]	Time 0.517 (0.575)	Data 0.001 (0.053)	Loss 1.470 (1.190)
Epoch: [12][140/200]	Time 0.522 (0.581)	Data 0.001 (0.058)	Loss 1.315 (1.243)
Epoch: [12][160/200]	Time 0.521 (0.574)	Data 0.000 (0.051)	Loss 1.261 (1.281)
Epoch: [12][180/200]	Time 0.522 (0.578)	Data 0.001 (0.055)	Loss 1.284 (1.298)
Epoch: [12][200/200]	Time 0.518 (0.581)	Data 0.001 (0.058)	Loss 2.080 (1.324)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.168 (0.215)	Data 0.000 (0.042)	
Extract Features: [100/128]	Time 0.170 (0.199)	Data 0.000 (0.025)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.951974868774414
==> Statistics for epoch 13: 1031 clusters
Epoch: [13][20/200]	Time 0.517 (0.575)	Data 0.001 (0.051)	Loss 0.387 (0.330)
Epoch: [13][40/200]	Time 0.517 (0.592)	Data 0.001 (0.071)	Loss 1.853 (0.565)
Epoch: [13][60/200]	Time 0.515 (0.567)	Data 0.000 (0.047)	Loss 1.349 (0.890)
Epoch: [13][80/200]	Time 0.517 (0.576)	Data 0.001 (0.055)	Loss 1.143 (1.046)
Epoch: [13][100/200]	Time 0.526 (0.583)	Data 0.002 (0.062)	Loss 1.333 (1.153)
Epoch: [13][120/200]	Time 0.519 (0.573)	Data 0.001 (0.051)	Loss 2.227 (1.225)
Epoch: [13][140/200]	Time 0.518 (0.579)	Data 0.001 (0.057)	Loss 1.389 (1.259)
Epoch: [13][160/200]	Time 0.517 (0.572)	Data 0.000 (0.050)	Loss 1.294 (1.297)
Epoch: [13][180/200]	Time 0.521 (0.576)	Data 0.001 (0.054)	Loss 1.531 (1.321)
Epoch: [13][200/200]	Time 0.519 (0.580)	Data 0.001 (0.057)	Loss 1.572 (1.339)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.169 (0.220)	Data 0.000 (0.047)	
Extract Features: [100/128]	Time 0.170 (0.200)	Data 0.000 (0.028)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.65972828865051
==> Statistics for epoch 14: 1053 clusters
Epoch: [14][20/200]	Time 0.514 (0.576)	Data 0.001 (0.059)	Loss 0.297 (0.327)
Epoch: [14][40/200]	Time 0.515 (0.589)	Data 0.001 (0.072)	Loss 1.480 (0.556)
Epoch: [14][60/200]	Time 0.516 (0.568)	Data 0.000 (0.048)	Loss 0.996 (0.880)
Epoch: [14][80/200]	Time 0.523 (0.578)	Data 0.001 (0.058)	Loss 1.271 (1.068)
Epoch: [14][100/200]	Time 0.524 (0.585)	Data 0.001 (0.064)	Loss 1.931 (1.159)
Epoch: [14][120/200]	Time 0.523 (0.575)	Data 0.001 (0.053)	Loss 1.350 (1.225)
Epoch: [14][140/200]	Time 0.521 (0.579)	Data 0.001 (0.058)	Loss 1.328 (1.266)
Epoch: [14][160/200]	Time 0.520 (0.573)	Data 0.000 (0.051)	Loss 1.792 (1.308)
Epoch: [14][180/200]	Time 0.524 (0.577)	Data 0.001 (0.055)	Loss 1.568 (1.343)
Epoch: [14][200/200]	Time 0.524 (0.580)	Data 0.000 (0.058)	Loss 1.619 (1.366)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.350 (0.211)	Data 0.175 (0.038)	
Extract Features: [100/128]	Time 0.174 (0.196)	Data 0.000 (0.022)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.03144192695618
==> Statistics for epoch 15: 1035 clusters
Epoch: [15][20/200]	Time 0.522 (0.575)	Data 0.001 (0.056)	Loss 0.388 (0.401)
Epoch: [15][40/200]	Time 0.519 (0.590)	Data 0.001 (0.068)	Loss 1.765 (0.609)
Epoch: [15][60/200]	Time 0.515 (0.566)	Data 0.000 (0.046)	Loss 1.646 (0.914)
Epoch: [15][80/200]	Time 0.516 (0.574)	Data 0.001 (0.054)	Loss 1.539 (1.084)
Epoch: [15][100/200]	Time 0.517 (0.578)	Data 0.001 (0.059)	Loss 1.082 (1.137)
Epoch: [15][120/200]	Time 0.517 (0.569)	Data 0.000 (0.049)	Loss 1.687 (1.196)
Epoch: [15][140/200]	Time 0.519 (0.573)	Data 0.001 (0.053)	Loss 1.471 (1.229)
Epoch: [15][160/200]	Time 0.517 (0.567)	Data 0.000 (0.046)	Loss 1.599 (1.266)
Epoch: [15][180/200]	Time 0.516 (0.571)	Data 0.001 (0.051)	Loss 1.182 (1.288)
Epoch: [15][200/200]	Time 0.520 (0.574)	Data 0.001 (0.053)	Loss 1.244 (1.305)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.168 (0.220)	Data 0.000 (0.048)	
Extract Features: [100/128]	Time 0.172 (0.201)	Data 0.000 (0.028)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.42893195152283
==> Statistics for epoch 16: 1039 clusters
Epoch: [16][20/200]	Time 0.518 (0.577)	Data 0.001 (0.058)	Loss 0.321 (0.336)
Epoch: [16][40/200]	Time 0.519 (0.589)	Data 0.000 (0.068)	Loss 1.344 (0.552)
Epoch: [16][60/200]	Time 0.517 (0.565)	Data 0.000 (0.045)	Loss 1.701 (0.871)
Epoch: [16][80/200]	Time 0.516 (0.574)	Data 0.001 (0.053)	Loss 1.199 (1.016)
Epoch: [16][100/200]	Time 0.522 (0.581)	Data 0.000 (0.059)	Loss 1.259 (1.092)
Epoch: [16][120/200]	Time 0.521 (0.571)	Data 0.000 (0.049)	Loss 1.095 (1.145)
Epoch: [16][140/200]	Time 0.519 (0.576)	Data 0.001 (0.054)	Loss 1.205 (1.193)
Epoch: [16][160/200]	Time 0.519 (0.569)	Data 0.000 (0.048)	Loss 1.048 (1.214)
Epoch: [16][180/200]	Time 0.519 (0.573)	Data 0.000 (0.051)	Loss 1.724 (1.239)
Epoch: [16][200/200]	Time 0.518 (0.577)	Data 0.000 (0.054)	Loss 1.287 (1.255)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.210)	Data 0.000 (0.036)	
Extract Features: [100/128]	Time 0.179 (0.195)	Data 0.000 (0.023)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.96606516838074
==> Statistics for epoch 17: 1042 clusters
Epoch: [17][20/200]	Time 0.636 (0.582)	Data 0.001 (0.057)	Loss 0.282 (0.317)
Epoch: [17][40/200]	Time 0.517 (0.592)	Data 0.001 (0.070)	Loss 1.327 (0.523)
Epoch: [17][60/200]	Time 0.514 (0.568)	Data 0.000 (0.047)	Loss 1.572 (0.834)
Epoch: [17][80/200]	Time 0.518 (0.576)	Data 0.001 (0.055)	Loss 1.502 (0.980)
Epoch: [17][100/200]	Time 0.527 (0.583)	Data 0.001 (0.061)	Loss 1.859 (1.076)
Epoch: [17][120/200]	Time 0.522 (0.572)	Data 0.001 (0.051)	Loss 1.349 (1.151)
Epoch: [17][140/200]	Time 0.525 (0.579)	Data 0.001 (0.057)	Loss 1.782 (1.210)
Epoch: [17][160/200]	Time 0.596 (0.573)	Data 0.000 (0.050)	Loss 1.436 (1.249)
Epoch: [17][180/200]	Time 0.518 (0.575)	Data 0.001 (0.053)	Loss 1.336 (1.273)
Epoch: [17][200/200]	Time 0.515 (0.578)	Data 0.000 (0.056)	Loss 1.764 (1.295)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.169 (0.211)	Data 0.000 (0.040)	
Extract Features: [100/128]	Time 0.171 (0.197)	Data 0.000 (0.024)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.78040552139282
==> Statistics for epoch 18: 1026 clusters
Epoch: [18][20/200]	Time 0.518 (0.575)	Data 0.000 (0.050)	Loss 0.298 (0.347)
Epoch: [18][40/200]	Time 0.519 (0.586)	Data 0.000 (0.063)	Loss 1.774 (0.574)
Epoch: [18][60/200]	Time 0.516 (0.565)	Data 0.000 (0.042)	Loss 1.522 (0.845)
Epoch: [18][80/200]	Time 0.517 (0.575)	Data 0.001 (0.053)	Loss 1.038 (0.987)
Epoch: [18][100/200]	Time 0.541 (0.580)	Data 0.001 (0.057)	Loss 1.368 (1.081)
Epoch: [18][120/200]	Time 0.519 (0.571)	Data 0.001 (0.048)	Loss 1.695 (1.142)
Epoch: [18][140/200]	Time 0.520 (0.575)	Data 0.001 (0.052)	Loss 1.476 (1.167)
Epoch: [18][160/200]	Time 0.520 (0.568)	Data 0.000 (0.045)	Loss 1.885 (1.196)
Epoch: [18][180/200]	Time 0.524 (0.573)	Data 0.000 (0.049)	Loss 1.629 (1.223)
Epoch: [18][200/200]	Time 0.522 (0.576)	Data 0.000 (0.053)	Loss 1.403 (1.233)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.168 (0.218)	Data 0.000 (0.045)	
Extract Features: [100/128]	Time 0.172 (0.201)	Data 0.000 (0.028)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.14718794822693
==> Statistics for epoch 19: 1032 clusters
Epoch: [19][20/200]	Time 0.514 (0.579)	Data 0.001 (0.056)	Loss 0.411 (0.464)
Epoch: [19][40/200]	Time 0.518 (0.589)	Data 0.001 (0.066)	Loss 0.934 (0.620)
Epoch: [19][60/200]	Time 0.516 (0.566)	Data 0.000 (0.044)	Loss 2.007 (0.893)
Epoch: [19][80/200]	Time 0.517 (0.575)	Data 0.001 (0.053)	Loss 1.019 (0.999)
Epoch: [19][100/200]	Time 0.520 (0.580)	Data 0.001 (0.059)	Loss 1.492 (1.065)
Epoch: [19][120/200]	Time 0.522 (0.571)	Data 0.001 (0.049)	Loss 1.368 (1.104)
Epoch: [19][140/200]	Time 0.517 (0.576)	Data 0.001 (0.054)	Loss 1.150 (1.128)
Epoch: [19][160/200]	Time 0.518 (0.569)	Data 0.000 (0.047)	Loss 1.296 (1.160)
Epoch: [19][180/200]	Time 0.517 (0.574)	Data 0.001 (0.051)	Loss 1.374 (1.175)
Epoch: [19][200/200]	Time 0.521 (0.576)	Data 0.001 (0.054)	Loss 1.484 (1.188)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.169 (0.214)	Data 0.000 (0.038)	
Extract Features: [100/128]	Time 0.173 (0.197)	Data 0.000 (0.022)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.992838859558105
==> Statistics for epoch 20: 1033 clusters
Epoch: [20][20/200]	Time 0.513 (0.586)	Data 0.001 (0.063)	Loss 0.226 (0.302)
Epoch: [20][40/200]	Time 0.517 (0.595)	Data 0.001 (0.073)	Loss 1.322 (0.499)
Epoch: [20][60/200]	Time 0.518 (0.569)	Data 0.000 (0.049)	Loss 1.339 (0.815)
Epoch: [20][80/200]	Time 0.515 (0.578)	Data 0.001 (0.056)	Loss 1.780 (0.973)
Epoch: [20][100/200]	Time 0.527 (0.583)	Data 0.001 (0.062)	Loss 1.315 (1.064)
Epoch: [20][120/200]	Time 0.533 (0.572)	Data 0.001 (0.051)	Loss 1.386 (1.121)
Epoch: [20][140/200]	Time 0.520 (0.577)	Data 0.000 (0.055)	Loss 1.295 (1.168)
Epoch: [20][160/200]	Time 0.522 (0.570)	Data 0.000 (0.049)	Loss 1.679 (1.197)
Epoch: [20][180/200]	Time 0.523 (0.574)	Data 0.001 (0.052)	Loss 1.365 (1.224)
Epoch: [20][200/200]	Time 0.518 (0.578)	Data 0.001 (0.056)	Loss 1.451 (1.245)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.171 (0.216)	Data 0.000 (0.039)	
Extract Features: [100/128]	Time 0.170 (0.196)	Data 0.000 (0.021)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.54495882987976
==> Statistics for epoch 21: 1043 clusters
Epoch: [21][20/200]	Time 0.594 (0.578)	Data 0.001 (0.055)	Loss 0.152 (0.255)
Epoch: [21][40/200]	Time 0.521 (0.590)	Data 0.001 (0.068)	Loss 1.302 (0.473)
Epoch: [21][60/200]	Time 0.517 (0.567)	Data 0.000 (0.045)	Loss 1.337 (0.774)
Epoch: [21][80/200]	Time 0.521 (0.576)	Data 0.002 (0.055)	Loss 1.373 (0.918)
Epoch: [21][100/200]	Time 0.529 (0.583)	Data 0.001 (0.062)	Loss 1.544 (1.033)
Epoch: [21][120/200]	Time 0.521 (0.573)	Data 0.001 (0.052)	Loss 1.613 (1.103)
Epoch: [21][140/200]	Time 0.520 (0.578)	Data 0.001 (0.056)	Loss 1.169 (1.137)
Epoch: [21][160/200]	Time 0.523 (0.571)	Data 0.000 (0.049)	Loss 1.388 (1.174)
Epoch: [21][180/200]	Time 0.523 (0.576)	Data 0.001 (0.053)	Loss 1.550 (1.198)
Epoch: [21][200/200]	Time 0.521 (0.580)	Data 0.001 (0.057)	Loss 1.818 (1.214)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.379 (0.212)	Data 0.212 (0.042)	
Extract Features: [100/128]	Time 0.170 (0.195)	Data 0.000 (0.023)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.64960741996765
==> Statistics for epoch 22: 1043 clusters
Epoch: [22][20/200]	Time 0.519 (0.576)	Data 0.001 (0.056)	Loss 0.338 (0.260)
Epoch: [22][40/200]	Time 0.520 (0.590)	Data 0.001 (0.070)	Loss 1.347 (0.462)
Epoch: [22][60/200]	Time 0.521 (0.569)	Data 0.000 (0.047)	Loss 1.723 (0.775)
Epoch: [22][80/200]	Time 0.518 (0.579)	Data 0.000 (0.058)	Loss 1.467 (0.944)
Epoch: [22][100/200]	Time 0.522 (0.586)	Data 0.001 (0.064)	Loss 1.778 (1.040)
Epoch: [22][120/200]	Time 0.523 (0.576)	Data 0.001 (0.054)	Loss 1.210 (1.103)
Epoch: [22][140/200]	Time 0.522 (0.580)	Data 0.001 (0.058)	Loss 1.448 (1.146)
Epoch: [22][160/200]	Time 0.516 (0.573)	Data 0.000 (0.051)	Loss 2.065 (1.180)
Epoch: [22][180/200]	Time 0.530 (0.577)	Data 0.001 (0.054)	Loss 1.502 (1.206)
Epoch: [22][200/200]	Time 0.516 (0.580)	Data 0.001 (0.057)	Loss 1.694 (1.226)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.219)	Data 0.000 (0.046)	
Extract Features: [100/128]	Time 0.172 (0.201)	Data 0.000 (0.027)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.93402886390686
==> Statistics for epoch 23: 1062 clusters
Epoch: [23][20/200]	Time 0.518 (0.579)	Data 0.001 (0.051)	Loss 0.240 (0.238)
Epoch: [23][40/200]	Time 0.518 (0.590)	Data 0.001 (0.066)	Loss 1.292 (0.413)
Epoch: [23][60/200]	Time 0.519 (0.567)	Data 0.000 (0.044)	Loss 1.621 (0.740)
Epoch: [23][80/200]	Time 0.519 (0.576)	Data 0.001 (0.054)	Loss 1.726 (0.879)
Epoch: [23][100/200]	Time 2.026 (0.582)	Data 1.481 (0.058)	Loss 1.443 (0.991)
Epoch: [23][120/200]	Time 0.522 (0.572)	Data 0.001 (0.049)	Loss 1.460 (1.078)
Epoch: [23][140/200]	Time 0.524 (0.577)	Data 0.001 (0.053)	Loss 1.088 (1.118)
Epoch: [23][160/200]	Time 0.517 (0.570)	Data 0.000 (0.047)	Loss 1.426 (1.165)
Epoch: [23][180/200]	Time 0.521 (0.574)	Data 0.001 (0.050)	Loss 1.351 (1.201)
Epoch: [23][200/200]	Time 0.521 (0.578)	Data 0.001 (0.055)	Loss 1.279 (1.214)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.171 (0.217)	Data 0.000 (0.042)	
Extract Features: [100/128]	Time 0.168 (0.198)	Data 0.000 (0.024)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.54353618621826
==> Statistics for epoch 24: 1060 clusters
Epoch: [24][20/200]	Time 0.517 (0.574)	Data 0.001 (0.056)	Loss 0.337 (0.261)
Epoch: [24][40/200]	Time 0.515 (0.588)	Data 0.001 (0.067)	Loss 1.705 (0.451)
Epoch: [24][60/200]	Time 0.516 (0.564)	Data 0.000 (0.045)	Loss 1.072 (0.767)
Epoch: [24][80/200]	Time 0.520 (0.574)	Data 0.001 (0.053)	Loss 1.256 (0.924)
Epoch: [24][100/200]	Time 2.289 (0.581)	Data 1.750 (0.060)	Loss 1.545 (1.018)
Epoch: [24][120/200]	Time 0.533 (0.572)	Data 0.001 (0.050)	Loss 1.792 (1.089)
Epoch: [24][140/200]	Time 0.518 (0.577)	Data 0.001 (0.055)	Loss 1.108 (1.130)
Epoch: [24][160/200]	Time 0.517 (0.569)	Data 0.000 (0.049)	Loss 1.835 (1.169)
Epoch: [24][180/200]	Time 0.518 (0.573)	Data 0.001 (0.052)	Loss 1.274 (1.198)
Epoch: [24][200/200]	Time 0.523 (0.576)	Data 0.001 (0.055)	Loss 1.435 (1.224)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.168 (0.217)	Data 0.000 (0.045)	
Extract Features: [100/128]	Time 0.179 (0.197)	Data 0.000 (0.026)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.953941345214844
==> Statistics for epoch 25: 1063 clusters
Epoch: [25][20/200]	Time 0.515 (0.566)	Data 0.000 (0.050)	Loss 0.242 (0.267)
Epoch: [25][40/200]	Time 0.518 (0.583)	Data 0.001 (0.066)	Loss 1.584 (0.438)
Epoch: [25][60/200]	Time 0.515 (0.563)	Data 0.000 (0.044)	Loss 1.180 (0.759)
Epoch: [25][80/200]	Time 0.518 (0.575)	Data 0.001 (0.054)	Loss 1.465 (0.949)
Epoch: [25][100/200]	Time 2.182 (0.581)	Data 1.636 (0.060)	Loss 1.610 (1.037)
Epoch: [25][120/200]	Time 0.520 (0.571)	Data 0.001 (0.050)	Loss 1.951 (1.112)
Epoch: [25][140/200]	Time 0.519 (0.576)	Data 0.000 (0.055)	Loss 1.975 (1.172)
Epoch: [25][160/200]	Time 0.518 (0.569)	Data 0.000 (0.048)	Loss 1.213 (1.195)
Epoch: [25][180/200]	Time 0.525 (0.573)	Data 0.002 (0.052)	Loss 1.658 (1.219)
Epoch: [25][200/200]	Time 0.524 (0.577)	Data 0.001 (0.055)	Loss 1.815 (1.239)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.168 (0.215)	Data 0.000 (0.042)	
Extract Features: [100/128]	Time 0.184 (0.200)	Data 0.000 (0.025)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.06594944000244
==> Statistics for epoch 26: 1054 clusters
Epoch: [26][20/200]	Time 0.518 (0.573)	Data 0.001 (0.056)	Loss 0.204 (0.251)
Epoch: [26][40/200]	Time 0.519 (0.589)	Data 0.001 (0.069)	Loss 1.354 (0.483)
Epoch: [26][60/200]	Time 0.516 (0.569)	Data 0.000 (0.046)	Loss 1.107 (0.744)
Epoch: [26][80/200]	Time 0.517 (0.580)	Data 0.001 (0.056)	Loss 1.390 (0.913)
Epoch: [26][100/200]	Time 0.523 (0.583)	Data 0.001 (0.060)	Loss 1.341 (0.993)
Epoch: [26][120/200]	Time 0.517 (0.572)	Data 0.001 (0.050)	Loss 1.897 (1.055)
Epoch: [26][140/200]	Time 0.518 (0.577)	Data 0.001 (0.055)	Loss 1.317 (1.109)
Epoch: [26][160/200]	Time 0.520 (0.571)	Data 0.000 (0.048)	Loss 0.935 (1.134)
Epoch: [26][180/200]	Time 0.528 (0.576)	Data 0.001 (0.053)	Loss 1.492 (1.163)
Epoch: [26][200/200]	Time 0.523 (0.580)	Data 0.001 (0.056)	Loss 1.701 (1.191)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.215)	Data 0.000 (0.041)	
Extract Features: [100/128]	Time 0.176 (0.199)	Data 0.000 (0.024)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.057231187820435
==> Statistics for epoch 27: 1045 clusters
Epoch: [27][20/200]	Time 0.524 (0.571)	Data 0.001 (0.052)	Loss 0.233 (0.267)
Epoch: [27][40/200]	Time 0.516 (0.588)	Data 0.001 (0.068)	Loss 0.902 (0.463)
Epoch: [27][60/200]	Time 0.518 (0.567)	Data 0.000 (0.046)	Loss 1.022 (0.759)
Epoch: [27][80/200]	Time 0.521 (0.576)	Data 0.001 (0.054)	Loss 2.077 (0.921)
Epoch: [27][100/200]	Time 0.527 (0.581)	Data 0.001 (0.059)	Loss 1.442 (1.006)
Epoch: [27][120/200]	Time 0.519 (0.573)	Data 0.001 (0.049)	Loss 1.458 (1.075)
Epoch: [27][140/200]	Time 0.648 (0.577)	Data 0.001 (0.053)	Loss 1.782 (1.122)
Epoch: [27][160/200]	Time 0.517 (0.570)	Data 0.000 (0.047)	Loss 1.374 (1.153)
Epoch: [27][180/200]	Time 0.522 (0.575)	Data 0.001 (0.050)	Loss 1.720 (1.183)
Epoch: [27][200/200]	Time 0.522 (0.577)	Data 0.001 (0.053)	Loss 1.263 (1.199)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.368 (0.217)	Data 0.191 (0.041)	
Extract Features: [100/128]	Time 0.171 (0.200)	Data 0.000 (0.023)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.844005823135376
==> Statistics for epoch 28: 1050 clusters
Epoch: [28][20/200]	Time 0.520 (0.574)	Data 0.001 (0.054)	Loss 0.260 (0.269)
Epoch: [28][40/200]	Time 0.518 (0.593)	Data 0.001 (0.072)	Loss 1.425 (0.445)
Epoch: [28][60/200]	Time 0.519 (0.569)	Data 0.000 (0.048)	Loss 1.392 (0.742)
Epoch: [28][80/200]	Time 0.519 (0.579)	Data 0.001 (0.058)	Loss 1.356 (0.923)
Epoch: [28][100/200]	Time 0.526 (0.586)	Data 0.001 (0.064)	Loss 1.473 (1.026)
Epoch: [28][120/200]	Time 0.519 (0.576)	Data 0.000 (0.053)	Loss 1.347 (1.096)
Epoch: [28][140/200]	Time 0.522 (0.580)	Data 0.001 (0.058)	Loss 1.706 (1.145)
Epoch: [28][160/200]	Time 0.520 (0.573)	Data 0.000 (0.050)	Loss 1.245 (1.175)
Epoch: [28][180/200]	Time 0.521 (0.577)	Data 0.001 (0.054)	Loss 1.505 (1.202)
Epoch: [28][200/200]	Time 0.524 (0.580)	Data 0.001 (0.056)	Loss 1.225 (1.219)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.177 (0.215)	Data 0.000 (0.038)	
Extract Features: [100/128]	Time 0.173 (0.196)	Data 0.000 (0.021)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.858755588531494
==> Statistics for epoch 29: 1054 clusters
Epoch: [29][20/200]	Time 0.617 (0.576)	Data 0.001 (0.054)	Loss 0.187 (0.265)
Epoch: [29][40/200]	Time 0.542 (0.587)	Data 0.001 (0.066)	Loss 1.181 (0.477)
Epoch: [29][60/200]	Time 0.520 (0.565)	Data 0.000 (0.044)	Loss 0.982 (0.760)
Epoch: [29][80/200]	Time 0.521 (0.575)	Data 0.001 (0.054)	Loss 1.318 (0.918)
Epoch: [29][100/200]	Time 0.521 (0.581)	Data 0.001 (0.060)	Loss 1.713 (0.997)
Epoch: [29][120/200]	Time 0.517 (0.571)	Data 0.001 (0.050)	Loss 1.559 (1.075)
Epoch: [29][140/200]	Time 0.521 (0.576)	Data 0.001 (0.055)	Loss 1.345 (1.126)
Epoch: [29][160/200]	Time 0.520 (0.569)	Data 0.000 (0.048)	Loss 1.702 (1.156)
Epoch: [29][180/200]	Time 0.521 (0.573)	Data 0.001 (0.052)	Loss 1.226 (1.186)
Epoch: [29][200/200]	Time 0.524 (0.577)	Data 0.001 (0.055)	Loss 1.457 (1.210)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.168 (0.216)	Data 0.000 (0.044)	
Extract Features: [100/128]	Time 0.170 (0.198)	Data 0.000 (0.026)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.423504114151
==> Statistics for epoch 30: 1060 clusters
Epoch: [30][20/200]	Time 0.514 (0.574)	Data 0.001 (0.055)	Loss 0.313 (0.272)
Epoch: [30][40/200]	Time 0.517 (0.594)	Data 0.001 (0.073)	Loss 1.513 (0.498)
Epoch: [30][60/200]	Time 0.521 (0.569)	Data 0.000 (0.049)	Loss 1.450 (0.768)
Epoch: [30][80/200]	Time 0.518 (0.582)	Data 0.001 (0.060)	Loss 1.178 (0.914)
Epoch: [30][100/200]	Time 2.324 (0.587)	Data 1.786 (0.066)	Loss 1.758 (1.018)
Epoch: [30][120/200]	Time 0.519 (0.577)	Data 0.001 (0.055)	Loss 1.557 (1.076)
Epoch: [30][140/200]	Time 0.520 (0.582)	Data 0.001 (0.060)	Loss 1.176 (1.118)
Epoch: [30][160/200]	Time 0.525 (0.575)	Data 0.000 (0.053)	Loss 1.420 (1.165)
Epoch: [30][180/200]	Time 0.522 (0.579)	Data 0.001 (0.056)	Loss 1.512 (1.192)
Epoch: [30][200/200]	Time 0.523 (0.582)	Data 0.001 (0.059)	Loss 1.476 (1.212)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.172 (0.214)	Data 0.000 (0.041)	
Extract Features: [100/128]	Time 0.176 (0.198)	Data 0.001 (0.024)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.52653932571411
==> Statistics for epoch 31: 1062 clusters
Epoch: [31][20/200]	Time 0.519 (0.576)	Data 0.001 (0.057)	Loss 0.124 (0.228)
Epoch: [31][40/200]	Time 0.517 (0.588)	Data 0.001 (0.070)	Loss 1.372 (0.441)
Epoch: [31][60/200]	Time 0.521 (0.567)	Data 0.000 (0.047)	Loss 1.407 (0.757)
Epoch: [31][80/200]	Time 0.530 (0.578)	Data 0.001 (0.056)	Loss 1.339 (0.921)
Epoch: [31][100/200]	Time 2.308 (0.586)	Data 1.758 (0.062)	Loss 1.011 (1.017)
Epoch: [31][120/200]	Time 0.523 (0.575)	Data 0.001 (0.052)	Loss 1.674 (1.081)
Epoch: [31][140/200]	Time 0.518 (0.580)	Data 0.001 (0.057)	Loss 1.296 (1.128)
Epoch: [31][160/200]	Time 0.516 (0.573)	Data 0.000 (0.050)	Loss 1.471 (1.149)
Epoch: [31][180/200]	Time 0.521 (0.576)	Data 0.001 (0.053)	Loss 0.787 (1.174)
Epoch: [31][200/200]	Time 0.526 (0.580)	Data 0.001 (0.056)	Loss 1.484 (1.198)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.213 (0.218)	Data 0.045 (0.048)	
Extract Features: [100/128]	Time 0.177 (0.201)	Data 0.000 (0.028)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.4328989982605
==> Statistics for epoch 32: 1064 clusters
Epoch: [32][20/200]	Time 0.518 (0.569)	Data 0.001 (0.050)	Loss 0.341 (0.255)
Epoch: [32][40/200]	Time 0.519 (0.589)	Data 0.001 (0.067)	Loss 1.500 (0.448)
Epoch: [32][60/200]	Time 0.519 (0.566)	Data 0.000 (0.045)	Loss 1.074 (0.767)
Epoch: [32][80/200]	Time 0.520 (0.577)	Data 0.001 (0.056)	Loss 1.637 (0.939)
Epoch: [32][100/200]	Time 2.240 (0.582)	Data 1.692 (0.062)	Loss 1.323 (1.018)
Epoch: [32][120/200]	Time 0.518 (0.573)	Data 0.001 (0.052)	Loss 1.671 (1.088)
Epoch: [32][140/200]	Time 0.522 (0.578)	Data 0.001 (0.056)	Loss 1.655 (1.135)
Epoch: [32][160/200]	Time 0.519 (0.572)	Data 0.000 (0.049)	Loss 1.360 (1.171)
Epoch: [32][180/200]	Time 0.520 (0.576)	Data 0.001 (0.053)	Loss 1.105 (1.195)
Epoch: [32][200/200]	Time 0.532 (0.580)	Data 0.001 (0.057)	Loss 1.230 (1.223)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.174 (0.212)	Data 0.009 (0.040)	
Extract Features: [100/128]	Time 0.169 (0.195)	Data 0.000 (0.023)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.127920627593994
==> Statistics for epoch 33: 1064 clusters
Epoch: [33][20/200]	Time 0.607 (0.575)	Data 0.001 (0.052)	Loss 0.375 (0.255)
Epoch: [33][40/200]	Time 0.516 (0.592)	Data 0.001 (0.071)	Loss 1.510 (0.445)
Epoch: [33][60/200]	Time 0.519 (0.567)	Data 0.000 (0.048)	Loss 1.577 (0.747)
Epoch: [33][80/200]	Time 0.526 (0.579)	Data 0.001 (0.058)	Loss 1.392 (0.892)
Epoch: [33][100/200]	Time 2.248 (0.584)	Data 1.715 (0.063)	Loss 1.202 (0.985)
Epoch: [33][120/200]	Time 0.519 (0.574)	Data 0.001 (0.053)	Loss 1.060 (1.058)
Epoch: [33][140/200]	Time 0.520 (0.580)	Data 0.001 (0.058)	Loss 1.016 (1.093)
Epoch: [33][160/200]	Time 0.518 (0.572)	Data 0.000 (0.051)	Loss 1.323 (1.146)
Epoch: [33][180/200]	Time 0.521 (0.576)	Data 0.001 (0.054)	Loss 1.238 (1.169)
Epoch: [33][200/200]	Time 0.521 (0.579)	Data 0.001 (0.057)	Loss 1.543 (1.189)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.215)	Data 0.000 (0.045)	
Extract Features: [100/128]	Time 0.172 (0.199)	Data 0.000 (0.027)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.91834878921509
==> Statistics for epoch 34: 1050 clusters
Epoch: [34][20/200]	Time 0.518 (0.579)	Data 0.001 (0.053)	Loss 0.421 (0.258)
Epoch: [34][40/200]	Time 0.518 (0.592)	Data 0.001 (0.070)	Loss 1.426 (0.469)
Epoch: [34][60/200]	Time 0.518 (0.571)	Data 0.000 (0.047)	Loss 1.175 (0.750)
Epoch: [34][80/200]	Time 0.519 (0.580)	Data 0.001 (0.057)	Loss 1.864 (0.926)
Epoch: [34][100/200]	Time 0.517 (0.587)	Data 0.001 (0.063)	Loss 1.407 (1.021)
Epoch: [34][120/200]	Time 0.525 (0.576)	Data 0.001 (0.053)	Loss 1.580 (1.071)
Epoch: [34][140/200]	Time 0.522 (0.582)	Data 0.001 (0.058)	Loss 1.718 (1.113)
Epoch: [34][160/200]	Time 0.522 (0.574)	Data 0.000 (0.051)	Loss 1.304 (1.147)
Epoch: [34][180/200]	Time 0.525 (0.579)	Data 0.000 (0.056)	Loss 1.084 (1.175)
Epoch: [34][200/200]	Time 0.520 (0.581)	Data 0.001 (0.058)	Loss 1.271 (1.192)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.214)	Data 0.000 (0.042)	
Extract Features: [100/128]	Time 0.171 (0.197)	Data 0.000 (0.025)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.795315980911255
==> Statistics for epoch 35: 1043 clusters
Epoch: [35][20/200]	Time 0.518 (0.574)	Data 0.001 (0.055)	Loss 0.164 (0.239)
Epoch: [35][40/200]	Time 0.516 (0.591)	Data 0.001 (0.069)	Loss 1.384 (0.436)
Epoch: [35][60/200]	Time 0.617 (0.569)	Data 0.000 (0.046)	Loss 1.216 (0.726)
Epoch: [35][80/200]	Time 0.520 (0.578)	Data 0.001 (0.055)	Loss 1.893 (0.866)
Epoch: [35][100/200]	Time 0.526 (0.584)	Data 0.001 (0.060)	Loss 1.285 (0.959)
Epoch: [35][120/200]	Time 0.520 (0.573)	Data 0.001 (0.050)	Loss 1.168 (1.017)
Epoch: [35][140/200]	Time 0.523 (0.579)	Data 0.001 (0.055)	Loss 1.223 (1.074)
Epoch: [35][160/200]	Time 0.516 (0.571)	Data 0.000 (0.048)	Loss 1.243 (1.097)
Epoch: [35][180/200]	Time 0.521 (0.576)	Data 0.001 (0.053)	Loss 1.338 (1.125)
Epoch: [35][200/200]	Time 0.517 (0.579)	Data 0.001 (0.056)	Loss 0.996 (1.148)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.166 (0.214)	Data 0.000 (0.040)	
Extract Features: [100/128]	Time 0.170 (0.198)	Data 0.000 (0.025)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.23414969444275
==> Statistics for epoch 36: 1054 clusters
Epoch: [36][20/200]	Time 0.515 (0.570)	Data 0.001 (0.052)	Loss 0.167 (0.232)
Epoch: [36][40/200]	Time 0.520 (0.593)	Data 0.001 (0.071)	Loss 1.376 (0.487)
Epoch: [36][60/200]	Time 0.519 (0.568)	Data 0.000 (0.048)	Loss 1.298 (0.759)
Epoch: [36][80/200]	Time 0.524 (0.581)	Data 0.001 (0.059)	Loss 1.548 (0.918)
Epoch: [36][100/200]	Time 0.525 (0.585)	Data 0.001 (0.063)	Loss 1.354 (1.003)
Epoch: [36][120/200]	Time 0.522 (0.574)	Data 0.001 (0.053)	Loss 1.442 (1.077)
Epoch: [36][140/200]	Time 0.520 (0.579)	Data 0.001 (0.057)	Loss 1.469 (1.115)
Epoch: [36][160/200]	Time 0.522 (0.573)	Data 0.000 (0.050)	Loss 1.693 (1.159)
Epoch: [36][180/200]	Time 0.518 (0.577)	Data 0.001 (0.054)	Loss 1.510 (1.183)
Epoch: [36][200/200]	Time 0.525 (0.580)	Data 0.001 (0.058)	Loss 1.591 (1.215)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.210)	Data 0.000 (0.037)	
Extract Features: [100/128]	Time 0.176 (0.194)	Data 0.000 (0.022)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.69155311584473
==> Statistics for epoch 37: 1066 clusters
Epoch: [37][20/200]	Time 0.515 (0.579)	Data 0.001 (0.060)	Loss 0.467 (0.247)
Epoch: [37][40/200]	Time 0.520 (0.591)	Data 0.001 (0.069)	Loss 1.374 (0.425)
Epoch: [37][60/200]	Time 0.519 (0.567)	Data 0.000 (0.046)	Loss 1.410 (0.733)
Epoch: [37][80/200]	Time 0.520 (0.574)	Data 0.001 (0.054)	Loss 1.540 (0.887)
Epoch: [37][100/200]	Time 2.225 (0.582)	Data 1.666 (0.060)	Loss 1.455 (0.976)
Epoch: [37][120/200]	Time 0.521 (0.572)	Data 0.001 (0.050)	Loss 1.455 (1.046)
Epoch: [37][140/200]	Time 0.519 (0.578)	Data 0.001 (0.055)	Loss 1.443 (1.088)
Epoch: [37][160/200]	Time 0.520 (0.571)	Data 0.000 (0.048)	Loss 1.065 (1.111)
Epoch: [37][180/200]	Time 0.521 (0.576)	Data 0.001 (0.053)	Loss 1.238 (1.139)
Epoch: [37][200/200]	Time 0.675 (0.580)	Data 0.001 (0.056)	Loss 1.421 (1.156)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.171 (0.222)	Data 0.000 (0.049)	
Extract Features: [100/128]	Time 0.173 (0.204)	Data 0.001 (0.029)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.16171717643738
==> Statistics for epoch 38: 1060 clusters
Epoch: [38][20/200]	Time 0.518 (0.570)	Data 0.001 (0.051)	Loss 0.107 (0.243)
Epoch: [38][40/200]	Time 0.516 (0.585)	Data 0.001 (0.064)	Loss 1.544 (0.423)
Epoch: [38][60/200]	Time 0.517 (0.562)	Data 0.000 (0.043)	Loss 1.344 (0.731)
Epoch: [38][80/200]	Time 0.515 (0.572)	Data 0.001 (0.052)	Loss 1.407 (0.872)
Epoch: [38][100/200]	Time 2.205 (0.579)	Data 1.659 (0.058)	Loss 1.592 (0.967)
Epoch: [38][120/200]	Time 0.524 (0.569)	Data 0.001 (0.049)	Loss 1.323 (1.036)
Epoch: [38][140/200]	Time 0.518 (0.575)	Data 0.001 (0.054)	Loss 1.424 (1.098)
Epoch: [38][160/200]	Time 0.522 (0.568)	Data 0.000 (0.047)	Loss 1.465 (1.144)
Epoch: [38][180/200]	Time 0.521 (0.573)	Data 0.001 (0.051)	Loss 1.197 (1.173)
Epoch: [38][200/200]	Time 0.524 (0.577)	Data 0.001 (0.055)	Loss 1.222 (1.187)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.169 (0.222)	Data 0.000 (0.047)	
Extract Features: [100/128]	Time 0.169 (0.201)	Data 0.000 (0.027)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.63628387451172
==> Statistics for epoch 39: 1055 clusters
Epoch: [39][20/200]	Time 0.517 (0.574)	Data 0.001 (0.055)	Loss 0.233 (0.243)
Epoch: [39][40/200]	Time 0.521 (0.588)	Data 0.001 (0.070)	Loss 1.012 (0.469)
Epoch: [39][60/200]	Time 0.518 (0.567)	Data 0.000 (0.047)	Loss 1.367 (0.737)
Epoch: [39][80/200]	Time 0.521 (0.577)	Data 0.001 (0.054)	Loss 1.493 (0.891)
Epoch: [39][100/200]	Time 0.526 (0.582)	Data 0.001 (0.059)	Loss 1.758 (0.986)
Epoch: [39][120/200]	Time 0.523 (0.572)	Data 0.001 (0.049)	Loss 1.545 (1.053)
Epoch: [39][140/200]	Time 0.525 (0.578)	Data 0.001 (0.054)	Loss 1.192 (1.095)
Epoch: [39][160/200]	Time 0.521 (0.571)	Data 0.000 (0.047)	Loss 1.077 (1.136)
Epoch: [39][180/200]	Time 0.522 (0.575)	Data 0.001 (0.052)	Loss 1.873 (1.168)
Epoch: [39][200/200]	Time 0.518 (0.579)	Data 0.001 (0.055)	Loss 1.026 (1.183)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.213)	Data 0.008 (0.039)	
Extract Features: [100/128]	Time 0.177 (0.199)	Data 0.000 (0.023)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.12746715545654
==> Statistics for epoch 40: 1055 clusters
Epoch: [40][20/200]	Time 0.519 (0.567)	Data 0.001 (0.048)	Loss 0.188 (0.273)
Epoch: [40][40/200]	Time 0.520 (0.585)	Data 0.001 (0.065)	Loss 1.150 (0.445)
Epoch: [40][60/200]	Time 0.517 (0.565)	Data 0.000 (0.043)	Loss 1.712 (0.762)
Epoch: [40][80/200]	Time 0.523 (0.573)	Data 0.001 (0.051)	Loss 1.381 (0.919)
Epoch: [40][100/200]	Time 0.528 (0.581)	Data 0.001 (0.058)	Loss 1.426 (1.004)
Epoch: [40][120/200]	Time 0.520 (0.571)	Data 0.001 (0.049)	Loss 1.434 (1.066)
Epoch: [40][140/200]	Time 0.518 (0.576)	Data 0.001 (0.053)	Loss 1.251 (1.098)
Epoch: [40][160/200]	Time 0.519 (0.569)	Data 0.000 (0.047)	Loss 1.602 (1.133)
Epoch: [40][180/200]	Time 0.523 (0.574)	Data 0.001 (0.050)	Loss 1.268 (1.159)
Epoch: [40][200/200]	Time 0.519 (0.576)	Data 0.001 (0.053)	Loss 1.355 (1.174)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.173 (0.216)	Data 0.000 (0.039)	
Extract Features: [100/128]	Time 0.170 (0.199)	Data 0.000 (0.024)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.10676693916321
==> Statistics for epoch 41: 1066 clusters
Epoch: [41][20/200]	Time 0.523 (0.568)	Data 0.001 (0.049)	Loss 0.201 (0.246)
Epoch: [41][40/200]	Time 0.516 (0.594)	Data 0.001 (0.071)	Loss 1.411 (0.436)
Epoch: [41][60/200]	Time 0.515 (0.569)	Data 0.000 (0.048)	Loss 1.236 (0.726)
Epoch: [41][80/200]	Time 0.518 (0.580)	Data 0.001 (0.057)	Loss 1.094 (0.881)
Epoch: [41][100/200]	Time 2.179 (0.584)	Data 1.629 (0.062)	Loss 1.086 (0.968)
Epoch: [41][120/200]	Time 0.522 (0.574)	Data 0.001 (0.052)	Loss 1.202 (1.035)
Epoch: [41][140/200]	Time 0.526 (0.578)	Data 0.001 (0.056)	Loss 1.275 (1.099)
Epoch: [41][160/200]	Time 0.519 (0.572)	Data 0.000 (0.049)	Loss 1.375 (1.118)
Epoch: [41][180/200]	Time 0.527 (0.576)	Data 0.001 (0.053)	Loss 1.123 (1.142)
Epoch: [41][200/200]	Time 0.539 (0.579)	Data 0.001 (0.056)	Loss 1.169 (1.165)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.172 (0.223)	Data 0.000 (0.050)	
Extract Features: [100/128]	Time 0.170 (0.201)	Data 0.000 (0.028)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.29168939590454
==> Statistics for epoch 42: 1062 clusters
Epoch: [42][20/200]	Time 0.518 (0.572)	Data 0.000 (0.053)	Loss 0.266 (0.251)
Epoch: [42][40/200]	Time 0.518 (0.585)	Data 0.001 (0.066)	Loss 1.258 (0.428)
Epoch: [42][60/200]	Time 0.524 (0.566)	Data 0.000 (0.044)	Loss 1.219 (0.732)
Epoch: [42][80/200]	Time 0.521 (0.577)	Data 0.001 (0.054)	Loss 1.168 (0.872)
Epoch: [42][100/200]	Time 2.301 (0.583)	Data 1.750 (0.061)	Loss 1.412 (0.968)
Epoch: [42][120/200]	Time 0.530 (0.574)	Data 0.001 (0.051)	Loss 1.852 (1.042)
Epoch: [42][140/200]	Time 0.519 (0.578)	Data 0.001 (0.056)	Loss 1.133 (1.085)
Epoch: [42][160/200]	Time 0.518 (0.571)	Data 0.000 (0.049)	Loss 1.272 (1.119)
Epoch: [42][180/200]	Time 0.519 (0.576)	Data 0.001 (0.053)	Loss 1.287 (1.146)
Epoch: [42][200/200]	Time 0.522 (0.579)	Data 0.001 (0.056)	Loss 1.097 (1.167)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.333 (0.209)	Data 0.164 (0.035)	
Extract Features: [100/128]	Time 0.170 (0.194)	Data 0.000 (0.018)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.4983766078949
==> Statistics for epoch 43: 1074 clusters
Epoch: [43][20/200]	Time 0.523 (0.582)	Data 0.001 (0.052)	Loss 0.184 (0.232)
Epoch: [43][40/200]	Time 0.524 (0.597)	Data 0.001 (0.068)	Loss 1.488 (0.412)
Epoch: [43][60/200]	Time 0.515 (0.571)	Data 0.000 (0.045)	Loss 1.635 (0.731)
Epoch: [43][80/200]	Time 0.519 (0.577)	Data 0.001 (0.053)	Loss 1.591 (0.887)
Epoch: [43][100/200]	Time 2.198 (0.582)	Data 1.649 (0.059)	Loss 1.540 (0.985)
Epoch: [43][120/200]	Time 0.521 (0.573)	Data 0.001 (0.050)	Loss 1.357 (1.044)
Epoch: [43][140/200]	Time 0.520 (0.577)	Data 0.001 (0.054)	Loss 1.710 (1.095)
Epoch: [43][160/200]	Time 0.519 (0.571)	Data 0.000 (0.047)	Loss 1.735 (1.128)
Epoch: [43][180/200]	Time 0.522 (0.574)	Data 0.001 (0.050)	Loss 1.154 (1.150)
Epoch: [43][200/200]	Time 0.528 (0.577)	Data 0.000 (0.053)	Loss 1.170 (1.161)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.173 (0.219)	Data 0.000 (0.046)	
Extract Features: [100/128]	Time 0.172 (0.201)	Data 0.000 (0.027)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.396496534347534
==> Statistics for epoch 44: 1061 clusters
Epoch: [44][20/200]	Time 0.516 (0.574)	Data 0.001 (0.054)	Loss 0.227 (0.272)
Epoch: [44][40/200]	Time 0.518 (0.592)	Data 0.001 (0.069)	Loss 1.595 (0.434)
Epoch: [44][60/200]	Time 0.517 (0.568)	Data 0.000 (0.046)	Loss 1.226 (0.767)
Epoch: [44][80/200]	Time 0.520 (0.580)	Data 0.000 (0.057)	Loss 1.517 (0.908)
Epoch: [44][100/200]	Time 2.205 (0.585)	Data 1.661 (0.062)	Loss 1.402 (1.004)
Epoch: [44][120/200]	Time 0.521 (0.576)	Data 0.000 (0.052)	Loss 1.308 (1.055)
Epoch: [44][140/200]	Time 0.521 (0.582)	Data 0.000 (0.057)	Loss 1.510 (1.100)
Epoch: [44][160/200]	Time 0.520 (0.574)	Data 0.000 (0.050)	Loss 1.918 (1.130)
Epoch: [44][180/200]	Time 0.524 (0.579)	Data 0.000 (0.054)	Loss 1.815 (1.163)
Epoch: [44][200/200]	Time 0.525 (0.582)	Data 0.001 (0.058)	Loss 1.276 (1.172)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.211)	Data 0.000 (0.038)	
Extract Features: [100/128]	Time 0.169 (0.196)	Data 0.000 (0.023)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.34074425697327
==> Statistics for epoch 45: 1061 clusters
Epoch: [45][20/200]	Time 0.519 (0.577)	Data 0.001 (0.057)	Loss 0.296 (0.255)
Epoch: [45][40/200]	Time 0.518 (0.595)	Data 0.001 (0.071)	Loss 1.369 (0.452)
Epoch: [45][60/200]	Time 0.519 (0.570)	Data 0.000 (0.048)	Loss 1.487 (0.734)
Epoch: [45][80/200]	Time 0.521 (0.579)	Data 0.001 (0.055)	Loss 1.604 (0.898)
Epoch: [45][100/200]	Time 2.112 (0.583)	Data 1.566 (0.060)	Loss 1.340 (0.981)
Epoch: [45][120/200]	Time 0.522 (0.574)	Data 0.001 (0.050)	Loss 1.673 (1.049)
Epoch: [45][140/200]	Time 0.522 (0.579)	Data 0.001 (0.055)	Loss 1.516 (1.089)
Epoch: [45][160/200]	Time 0.517 (0.573)	Data 0.000 (0.048)	Loss 1.316 (1.132)
Epoch: [45][180/200]	Time 0.521 (0.577)	Data 0.001 (0.052)	Loss 1.077 (1.156)
Epoch: [45][200/200]	Time 0.529 (0.580)	Data 0.001 (0.056)	Loss 1.464 (1.179)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.169 (0.220)	Data 0.000 (0.044)	
Extract Features: [100/128]	Time 0.173 (0.201)	Data 0.000 (0.026)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.013720750808716
==> Statistics for epoch 46: 1058 clusters
Epoch: [46][20/200]	Time 0.518 (0.570)	Data 0.001 (0.052)	Loss 0.207 (0.234)
Epoch: [46][40/200]	Time 0.517 (0.589)	Data 0.001 (0.068)	Loss 1.523 (0.423)
Epoch: [46][60/200]	Time 0.513 (0.567)	Data 0.000 (0.045)	Loss 1.394 (0.711)
Epoch: [46][80/200]	Time 0.522 (0.576)	Data 0.000 (0.055)	Loss 1.341 (0.865)
Epoch: [46][100/200]	Time 2.141 (0.582)	Data 1.585 (0.060)	Loss 1.761 (0.974)
Epoch: [46][120/200]	Time 0.523 (0.573)	Data 0.001 (0.050)	Loss 1.322 (1.032)
Epoch: [46][140/200]	Time 0.518 (0.578)	Data 0.001 (0.055)	Loss 1.494 (1.081)
Epoch: [46][160/200]	Time 0.516 (0.571)	Data 0.000 (0.048)	Loss 1.275 (1.116)
Epoch: [46][180/200]	Time 0.520 (0.574)	Data 0.001 (0.052)	Loss 1.171 (1.146)
Epoch: [46][200/200]	Time 0.520 (0.577)	Data 0.001 (0.054)	Loss 1.163 (1.172)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.217)	Data 0.000 (0.041)	
Extract Features: [100/128]	Time 0.177 (0.199)	Data 0.000 (0.025)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.83310532569885
==> Statistics for epoch 47: 1061 clusters
Epoch: [47][20/200]	Time 0.518 (0.580)	Data 0.001 (0.056)	Loss 0.177 (0.233)
Epoch: [47][40/200]	Time 0.522 (0.591)	Data 0.001 (0.069)	Loss 1.324 (0.406)
Epoch: [47][60/200]	Time 0.518 (0.570)	Data 0.000 (0.046)	Loss 1.291 (0.709)
Epoch: [47][80/200]	Time 0.520 (0.580)	Data 0.001 (0.057)	Loss 1.251 (0.871)
Epoch: [47][100/200]	Time 2.196 (0.585)	Data 1.652 (0.062)	Loss 1.377 (0.954)
Epoch: [47][120/200]	Time 0.520 (0.575)	Data 0.001 (0.052)	Loss 1.499 (1.021)
Epoch: [47][140/200]	Time 0.522 (0.580)	Data 0.001 (0.057)	Loss 1.326 (1.066)
Epoch: [47][160/200]	Time 0.523 (0.574)	Data 0.000 (0.050)	Loss 1.338 (1.111)
Epoch: [47][180/200]	Time 0.517 (0.577)	Data 0.001 (0.053)	Loss 1.090 (1.139)
Epoch: [47][200/200]	Time 0.530 (0.580)	Data 0.001 (0.056)	Loss 1.326 (1.165)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.169 (0.215)	Data 0.000 (0.043)	
Extract Features: [100/128]	Time 0.173 (0.198)	Data 0.000 (0.027)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.67718958854675
==> Statistics for epoch 48: 1064 clusters
Epoch: [48][20/200]	Time 0.519 (0.571)	Data 0.001 (0.051)	Loss 0.286 (0.226)
Epoch: [48][40/200]	Time 0.519 (0.590)	Data 0.001 (0.070)	Loss 1.782 (0.432)
Epoch: [48][60/200]	Time 0.521 (0.569)	Data 0.000 (0.047)	Loss 1.595 (0.709)
Epoch: [48][80/200]	Time 0.519 (0.577)	Data 0.001 (0.055)	Loss 1.111 (0.869)
Epoch: [48][100/200]	Time 2.189 (0.584)	Data 1.642 (0.061)	Loss 1.847 (0.970)
Epoch: [48][120/200]	Time 0.516 (0.574)	Data 0.001 (0.051)	Loss 2.013 (1.061)
Epoch: [48][140/200]	Time 0.517 (0.580)	Data 0.001 (0.057)	Loss 1.353 (1.096)
Epoch: [48][160/200]	Time 0.519 (0.573)	Data 0.000 (0.050)	Loss 1.598 (1.139)
Epoch: [48][180/200]	Time 0.520 (0.575)	Data 0.001 (0.053)	Loss 1.408 (1.162)
Epoch: [48][200/200]	Time 0.521 (0.579)	Data 0.001 (0.056)	Loss 1.279 (1.182)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.209)	Data 0.000 (0.034)	
Extract Features: [100/128]	Time 0.170 (0.194)	Data 0.000 (0.021)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.041176319122314
==> Statistics for epoch 49: 1073 clusters
Epoch: [49][20/200]	Time 0.518 (0.574)	Data 0.001 (0.055)	Loss 0.330 (0.253)
Epoch: [49][40/200]	Time 0.521 (0.592)	Data 0.001 (0.073)	Loss 1.415 (0.412)
Epoch: [49][60/200]	Time 0.521 (0.569)	Data 0.000 (0.049)	Loss 1.174 (0.708)
Epoch: [49][80/200]	Time 0.523 (0.580)	Data 0.001 (0.059)	Loss 1.208 (0.873)
Epoch: [49][100/200]	Time 2.130 (0.584)	Data 1.575 (0.063)	Loss 1.104 (0.940)
Epoch: [49][120/200]	Time 0.522 (0.575)	Data 0.001 (0.052)	Loss 1.188 (1.013)
Epoch: [49][140/200]	Time 0.522 (0.580)	Data 0.001 (0.057)	Loss 1.715 (1.063)
Epoch: [49][160/200]	Time 0.520 (0.574)	Data 0.000 (0.050)	Loss 1.350 (1.108)
Epoch: [49][180/200]	Time 0.523 (0.577)	Data 0.001 (0.054)	Loss 1.305 (1.134)
Epoch: [49][200/200]	Time 0.524 (0.581)	Data 0.001 (0.057)	Loss 1.592 (1.158)
Extract Features: [50/367]	Time 0.177 (0.212)	Data 0.000 (0.041)	
Extract Features: [100/367]	Time 0.173 (0.198)	Data 0.000 (0.026)	
Extract Features: [150/367]	Time 0.177 (0.196)	Data 0.000 (0.023)	
Extract Features: [200/367]	Time 0.168 (0.192)	Data 0.000 (0.018)	
Extract Features: [250/367]	Time 0.166 (0.190)	Data 0.000 (0.015)	
Extract Features: [300/367]	Time 0.174 (0.190)	Data 0.000 (0.013)	
Extract Features: [350/367]	Time 0.169 (0.189)	Data 0.000 (0.011)	
Mean AP: 64.2%

 * Finished epoch  49  model mAP: 64.2%  best: 64.2% *

==> Test with the best model:
=> Loaded checkpoint 'log/msmt17/resnet101_cion/model_best.pth.tar'
Extract Features: [50/367]	Time 0.241 (0.218)	Data 0.076 (0.048)	
Extract Features: [100/367]	Time 0.168 (0.205)	Data 0.000 (0.034)	
Extract Features: [150/367]	Time 0.219 (0.197)	Data 0.052 (0.027)	
Extract Features: [200/367]	Time 0.165 (0.193)	Data 0.000 (0.023)	
Extract Features: [250/367]	Time 0.174 (0.191)	Data 0.004 (0.020)	
Extract Features: [300/367]	Time 0.169 (0.190)	Data 0.000 (0.019)	
Extract Features: [350/367]	Time 0.167 (0.189)	Data 0.000 (0.018)	
Mean AP: 64.2%
CMC Scores:
  top-1          85.2%
  top-5          91.6%
  top-10         93.2%
Total running time:  3:07:06.682073
