==========
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='resnet50', pretrained_path='/home/ma-user/work/Projects/ReIDNets_Checkpoints_TransReID/ResNet50_ViTdefault_2468_406080100_bs120_originaldino_noreid.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/resnet50_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 0.271 (0.361)	Data 0.157 (0.077)	
Extract Features: [100/128]	Time 0.115 (0.271)	Data 0.000 (0.071)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.005584955215454
Clustering criterion: eps: 0.700
==> Statistics for epoch 0: 965 clusters
Epoch: [0][20/200]	Time 0.353 (0.780)	Data 0.001 (0.052)	Loss 2.870 (2.739)
Epoch: [0][40/200]	Time 0.355 (0.607)	Data 0.001 (0.065)	Loss 2.904 (2.885)
Epoch: [0][60/200]	Time 0.352 (0.526)	Data 0.000 (0.044)	Loss 4.023 (3.128)
Epoch: [0][80/200]	Time 0.353 (0.503)	Data 0.001 (0.052)	Loss 2.754 (3.006)
Epoch: [0][100/200]	Time 0.360 (0.489)	Data 0.001 (0.057)	Loss 1.815 (2.891)
Epoch: [0][120/200]	Time 0.354 (0.467)	Data 0.000 (0.048)	Loss 2.433 (2.812)
Epoch: [0][140/200]	Time 0.363 (0.461)	Data 0.001 (0.051)	Loss 2.198 (2.730)
Epoch: [0][160/200]	Time 0.356 (0.458)	Data 0.001 (0.055)	Loss 2.303 (2.685)
Epoch: [0][180/200]	Time 0.349 (0.448)	Data 0.000 (0.049)	Loss 2.255 (2.629)
Epoch: [0][200/200]	Time 0.357 (0.446)	Data 0.001 (0.051)	Loss 2.248 (2.588)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.212)	Data 0.000 (0.098)	
Extract Features: [100/128]	Time 0.116 (0.192)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.37109875679016
==> Statistics for epoch 1: 1099 clusters
Epoch: [1][20/200]	Time 0.354 (0.400)	Data 0.001 (0.043)	Loss 0.915 (0.894)
Epoch: [1][40/200]	Time 0.351 (0.418)	Data 0.001 (0.063)	Loss 2.361 (1.043)
Epoch: [1][60/200]	Time 0.358 (0.397)	Data 0.001 (0.042)	Loss 2.205 (1.400)
Epoch: [1][80/200]	Time 0.358 (0.408)	Data 0.001 (0.052)	Loss 2.043 (1.545)
Epoch: [1][100/200]	Time 0.358 (0.398)	Data 0.000 (0.042)	Loss 1.905 (1.618)
Epoch: [1][120/200]	Time 0.357 (0.406)	Data 0.001 (0.049)	Loss 1.361 (1.639)
Epoch: [1][140/200]	Time 0.357 (0.410)	Data 0.001 (0.053)	Loss 2.079 (1.680)
Epoch: [1][160/200]	Time 0.357 (0.403)	Data 0.001 (0.046)	Loss 1.654 (1.690)
Epoch: [1][180/200]	Time 0.357 (0.407)	Data 0.001 (0.050)	Loss 2.052 (1.699)
Epoch: [1][200/200]	Time 0.353 (0.402)	Data 0.000 (0.045)	Loss 2.075 (1.701)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.254 (0.215)	Data 0.140 (0.096)	
Extract Features: [100/128]	Time 0.125 (0.194)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.69201326370239
==> Statistics for epoch 2: 1080 clusters
Epoch: [2][20/200]	Time 0.352 (0.409)	Data 0.000 (0.047)	Loss 0.432 (0.597)
Epoch: [2][40/200]	Time 0.357 (0.423)	Data 0.001 (0.065)	Loss 1.963 (0.813)
Epoch: [2][60/200]	Time 0.354 (0.400)	Data 0.000 (0.044)	Loss 1.757 (1.176)
Epoch: [2][80/200]	Time 0.353 (0.409)	Data 0.001 (0.054)	Loss 1.743 (1.353)
Epoch: [2][100/200]	Time 1.996 (0.415)	Data 1.618 (0.059)	Loss 2.272 (1.455)
Epoch: [2][120/200]	Time 0.355 (0.405)	Data 0.001 (0.050)	Loss 1.653 (1.512)
Epoch: [2][140/200]	Time 0.359 (0.409)	Data 0.001 (0.053)	Loss 1.784 (1.535)
Epoch: [2][160/200]	Time 0.360 (0.404)	Data 0.000 (0.047)	Loss 1.825 (1.564)
Epoch: [2][180/200]	Time 0.357 (0.408)	Data 0.001 (0.051)	Loss 1.819 (1.578)
Epoch: [2][200/200]	Time 0.353 (0.411)	Data 0.001 (0.054)	Loss 1.643 (1.596)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.234 (0.210)	Data 0.119 (0.095)	
Extract Features: [100/128]	Time 0.279 (0.193)	Data 0.163 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.84682941436768
==> Statistics for epoch 3: 1019 clusters
Epoch: [3][20/200]	Time 0.354 (0.408)	Data 0.001 (0.052)	Loss 0.710 (0.533)
Epoch: [3][40/200]	Time 0.358 (0.425)	Data 0.001 (0.063)	Loss 2.009 (0.794)
Epoch: [3][60/200]	Time 0.354 (0.403)	Data 0.000 (0.043)	Loss 2.340 (1.143)
Epoch: [3][80/200]	Time 0.355 (0.412)	Data 0.001 (0.052)	Loss 2.209 (1.335)
Epoch: [3][100/200]	Time 0.356 (0.417)	Data 0.001 (0.058)	Loss 2.306 (1.468)
Epoch: [3][120/200]	Time 0.354 (0.407)	Data 0.000 (0.049)	Loss 1.652 (1.521)
Epoch: [3][140/200]	Time 0.356 (0.412)	Data 0.001 (0.054)	Loss 1.381 (1.537)
Epoch: [3][160/200]	Time 0.355 (0.416)	Data 0.000 (0.057)	Loss 2.122 (1.581)
Epoch: [3][180/200]	Time 0.354 (0.410)	Data 0.000 (0.051)	Loss 1.985 (1.607)
Epoch: [3][200/200]	Time 0.357 (0.413)	Data 0.000 (0.054)	Loss 1.838 (1.625)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.210)	Data 0.000 (0.095)	
Extract Features: [100/128]	Time 0.116 (0.192)	Data 0.000 (0.075)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.74395251274109
==> Statistics for epoch 4: 1034 clusters
Epoch: [4][20/200]	Time 0.356 (0.404)	Data 0.001 (0.046)	Loss 0.523 (0.457)
Epoch: [4][40/200]	Time 0.355 (0.423)	Data 0.001 (0.067)	Loss 2.117 (0.717)
Epoch: [4][60/200]	Time 0.354 (0.401)	Data 0.000 (0.045)	Loss 1.804 (1.079)
Epoch: [4][80/200]	Time 0.356 (0.415)	Data 0.001 (0.057)	Loss 1.635 (1.265)
Epoch: [4][100/200]	Time 0.357 (0.420)	Data 0.001 (0.063)	Loss 1.985 (1.385)
Epoch: [4][120/200]	Time 0.363 (0.410)	Data 0.001 (0.052)	Loss 1.034 (1.448)
Epoch: [4][140/200]	Time 0.357 (0.415)	Data 0.001 (0.057)	Loss 1.856 (1.497)
Epoch: [4][160/200]	Time 0.355 (0.408)	Data 0.000 (0.050)	Loss 1.719 (1.530)
Epoch: [4][180/200]	Time 0.362 (0.411)	Data 0.001 (0.054)	Loss 1.456 (1.550)
Epoch: [4][200/200]	Time 0.358 (0.415)	Data 0.001 (0.057)	Loss 1.749 (1.578)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.117 (0.221)	Data 0.001 (0.106)	
Extract Features: [100/128]	Time 0.115 (0.199)	Data 0.000 (0.081)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.84561800956726
==> Statistics for epoch 5: 1052 clusters
Epoch: [5][20/200]	Time 0.352 (0.411)	Data 0.001 (0.053)	Loss 0.629 (0.561)
Epoch: [5][40/200]	Time 0.359 (0.423)	Data 0.001 (0.066)	Loss 1.065 (0.729)
Epoch: [5][60/200]	Time 0.355 (0.401)	Data 0.000 (0.044)	Loss 2.086 (1.071)
Epoch: [5][80/200]	Time 0.354 (0.411)	Data 0.000 (0.054)	Loss 1.953 (1.220)
Epoch: [5][100/200]	Time 0.357 (0.417)	Data 0.000 (0.060)	Loss 1.683 (1.326)
Epoch: [5][120/200]	Time 0.365 (0.407)	Data 0.001 (0.050)	Loss 1.471 (1.384)
Epoch: [5][140/200]	Time 0.364 (0.414)	Data 0.001 (0.056)	Loss 1.328 (1.428)
Epoch: [5][160/200]	Time 0.355 (0.407)	Data 0.000 (0.049)	Loss 1.664 (1.460)
Epoch: [5][180/200]	Time 0.358 (0.411)	Data 0.001 (0.053)	Loss 2.109 (1.482)
Epoch: [5][200/200]	Time 0.359 (0.415)	Data 0.001 (0.056)	Loss 1.502 (1.504)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.113 (0.215)	Data 0.000 (0.096)	
Extract Features: [100/128]	Time 0.117 (0.190)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.337833642959595
==> Statistics for epoch 6: 1054 clusters
Epoch: [6][20/200]	Time 0.356 (0.411)	Data 0.001 (0.055)	Loss 0.464 (0.496)
Epoch: [6][40/200]	Time 0.350 (0.421)	Data 0.001 (0.066)	Loss 1.855 (0.747)
Epoch: [6][60/200]	Time 0.351 (0.399)	Data 0.000 (0.044)	Loss 1.908 (1.040)
Epoch: [6][80/200]	Time 0.352 (0.411)	Data 0.001 (0.055)	Loss 1.785 (1.214)
Epoch: [6][100/200]	Time 0.354 (0.418)	Data 0.001 (0.061)	Loss 0.978 (1.289)
Epoch: [6][120/200]	Time 0.350 (0.407)	Data 0.001 (0.051)	Loss 1.517 (1.373)
Epoch: [6][140/200]	Time 0.359 (0.413)	Data 0.001 (0.056)	Loss 1.577 (1.417)
Epoch: [6][160/200]	Time 0.353 (0.405)	Data 0.000 (0.049)	Loss 1.104 (1.448)
Epoch: [6][180/200]	Time 0.358 (0.409)	Data 0.001 (0.053)	Loss 2.392 (1.477)
Epoch: [6][200/200]	Time 0.359 (0.412)	Data 0.001 (0.055)	Loss 1.753 (1.493)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.124 (0.210)	Data 0.010 (0.091)	
Extract Features: [100/128]	Time 0.117 (0.193)	Data 0.000 (0.075)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.705907583236694
==> Statistics for epoch 7: 1059 clusters
Epoch: [7][20/200]	Time 0.353 (0.414)	Data 0.001 (0.055)	Loss 0.416 (0.476)
Epoch: [7][40/200]	Time 0.356 (0.426)	Data 0.001 (0.070)	Loss 1.442 (0.665)
Epoch: [7][60/200]	Time 0.360 (0.403)	Data 0.000 (0.047)	Loss 1.563 (1.054)
Epoch: [7][80/200]	Time 0.371 (0.411)	Data 0.001 (0.055)	Loss 1.768 (1.242)
Epoch: [7][100/200]	Time 2.063 (0.417)	Data 1.679 (0.061)	Loss 1.465 (1.324)
Epoch: [7][120/200]	Time 0.356 (0.407)	Data 0.001 (0.051)	Loss 1.494 (1.383)
Epoch: [7][140/200]	Time 0.357 (0.414)	Data 0.001 (0.056)	Loss 1.536 (1.426)
Epoch: [7][160/200]	Time 0.358 (0.407)	Data 0.000 (0.049)	Loss 1.994 (1.457)
Epoch: [7][180/200]	Time 0.355 (0.411)	Data 0.001 (0.053)	Loss 1.761 (1.490)
Epoch: [7][200/200]	Time 0.354 (0.414)	Data 0.001 (0.056)	Loss 1.242 (1.506)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.113 (0.215)	Data 0.000 (0.097)	
Extract Features: [100/128]	Time 0.168 (0.193)	Data 0.041 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.97582268714905
==> Statistics for epoch 8: 1055 clusters
Epoch: [8][20/200]	Time 0.355 (0.410)	Data 0.001 (0.053)	Loss 0.369 (0.512)
Epoch: [8][40/200]	Time 0.354 (0.425)	Data 0.001 (0.069)	Loss 1.942 (0.744)
Epoch: [8][60/200]	Time 0.351 (0.402)	Data 0.000 (0.046)	Loss 1.937 (1.081)
Epoch: [8][80/200]	Time 0.360 (0.414)	Data 0.001 (0.058)	Loss 1.475 (1.245)
Epoch: [8][100/200]	Time 0.357 (0.418)	Data 0.002 (0.061)	Loss 2.054 (1.350)
Epoch: [8][120/200]	Time 0.356 (0.408)	Data 0.001 (0.051)	Loss 1.461 (1.414)
Epoch: [8][140/200]	Time 0.360 (0.414)	Data 0.001 (0.056)	Loss 1.787 (1.458)
Epoch: [8][160/200]	Time 0.356 (0.407)	Data 0.000 (0.049)	Loss 1.909 (1.482)
Epoch: [8][180/200]	Time 0.361 (0.411)	Data 0.001 (0.053)	Loss 1.547 (1.501)
Epoch: [8][200/200]	Time 0.365 (0.414)	Data 0.001 (0.056)	Loss 1.602 (1.523)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.359 (0.211)	Data 0.246 (0.093)	
Extract Features: [100/128]	Time 0.114 (0.192)	Data 0.000 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.79224896430969
==> Statistics for epoch 9: 1002 clusters
Epoch: [9][20/200]	Time 0.355 (0.414)	Data 0.001 (0.057)	Loss 0.328 (0.374)
Epoch: [9][40/200]	Time 0.355 (0.427)	Data 0.000 (0.070)	Loss 1.504 (0.669)
Epoch: [9][60/200]	Time 0.356 (0.403)	Data 0.000 (0.047)	Loss 1.662 (1.012)
Epoch: [9][80/200]	Time 0.356 (0.412)	Data 0.001 (0.055)	Loss 1.333 (1.190)
Epoch: [9][100/200]	Time 0.369 (0.419)	Data 0.001 (0.061)	Loss 2.077 (1.300)
Epoch: [9][120/200]	Time 0.355 (0.409)	Data 0.000 (0.051)	Loss 2.049 (1.374)
Epoch: [9][140/200]	Time 0.354 (0.414)	Data 0.001 (0.056)	Loss 1.757 (1.423)
Epoch: [9][160/200]	Time 0.356 (0.417)	Data 0.001 (0.060)	Loss 1.973 (1.461)
Epoch: [9][180/200]	Time 0.357 (0.411)	Data 0.000 (0.053)	Loss 1.825 (1.492)
Epoch: [9][200/200]	Time 0.359 (0.414)	Data 0.001 (0.056)	Loss 1.618 (1.515)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.210)	Data 0.000 (0.093)	
Extract Features: [100/128]	Time 0.117 (0.191)	Data 0.000 (0.075)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.03277778625488
==> Statistics for epoch 10: 1016 clusters
Epoch: [10][20/200]	Time 0.356 (0.412)	Data 0.001 (0.054)	Loss 0.342 (0.402)
Epoch: [10][40/200]	Time 0.350 (0.430)	Data 0.001 (0.071)	Loss 1.730 (0.685)
Epoch: [10][60/200]	Time 0.352 (0.406)	Data 0.000 (0.048)	Loss 1.312 (1.042)
Epoch: [10][80/200]	Time 0.355 (0.416)	Data 0.001 (0.058)	Loss 1.765 (1.227)
Epoch: [10][100/200]	Time 0.357 (0.421)	Data 0.001 (0.064)	Loss 1.989 (1.354)
Epoch: [10][120/200]	Time 0.353 (0.410)	Data 0.000 (0.053)	Loss 2.070 (1.422)
Epoch: [10][140/200]	Time 0.357 (0.415)	Data 0.001 (0.058)	Loss 1.689 (1.498)
Epoch: [10][160/200]	Time 0.354 (0.419)	Data 0.001 (0.062)	Loss 2.010 (1.529)
Epoch: [10][180/200]	Time 0.356 (0.413)	Data 0.000 (0.055)	Loss 1.598 (1.556)
Epoch: [10][200/200]	Time 0.354 (0.416)	Data 0.001 (0.058)	Loss 1.638 (1.577)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.215)	Data 0.000 (0.100)	
Extract Features: [100/128]	Time 0.116 (0.193)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.46017122268677
==> Statistics for epoch 11: 1021 clusters
Epoch: [11][20/200]	Time 0.360 (0.413)	Data 0.001 (0.057)	Loss 0.577 (0.438)
Epoch: [11][40/200]	Time 0.357 (0.427)	Data 0.001 (0.072)	Loss 1.686 (0.726)
Epoch: [11][60/200]	Time 0.356 (0.405)	Data 0.000 (0.048)	Loss 1.803 (1.058)
Epoch: [11][80/200]	Time 0.354 (0.415)	Data 0.001 (0.057)	Loss 1.484 (1.217)
Epoch: [11][100/200]	Time 0.354 (0.422)	Data 0.001 (0.064)	Loss 2.124 (1.330)
Epoch: [11][120/200]	Time 0.355 (0.411)	Data 0.000 (0.054)	Loss 1.455 (1.387)
Epoch: [11][140/200]	Time 0.357 (0.416)	Data 0.001 (0.059)	Loss 2.015 (1.448)
Epoch: [11][160/200]	Time 0.358 (0.420)	Data 0.001 (0.062)	Loss 1.614 (1.483)
Epoch: [11][180/200]	Time 0.355 (0.413)	Data 0.000 (0.056)	Loss 1.509 (1.509)
Epoch: [11][200/200]	Time 0.361 (0.417)	Data 0.001 (0.059)	Loss 1.473 (1.531)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.256 (0.220)	Data 0.000 (0.102)	
Extract Features: [100/128]	Time 0.123 (0.194)	Data 0.007 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.34465503692627
==> Statistics for epoch 12: 1073 clusters
Epoch: [12][20/200]	Time 0.353 (0.411)	Data 0.001 (0.052)	Loss 0.376 (0.407)
Epoch: [12][40/200]	Time 0.355 (0.431)	Data 0.000 (0.070)	Loss 1.733 (0.616)
Epoch: [12][60/200]	Time 0.355 (0.406)	Data 0.000 (0.047)	Loss 1.761 (0.987)
Epoch: [12][80/200]	Time 0.355 (0.415)	Data 0.001 (0.057)	Loss 1.889 (1.186)
Epoch: [12][100/200]	Time 2.054 (0.421)	Data 1.677 (0.062)	Loss 1.546 (1.316)
Epoch: [12][120/200]	Time 0.358 (0.410)	Data 0.001 (0.052)	Loss 1.386 (1.399)
Epoch: [12][140/200]	Time 0.359 (0.415)	Data 0.001 (0.057)	Loss 2.256 (1.454)
Epoch: [12][160/200]	Time 0.352 (0.408)	Data 0.000 (0.050)	Loss 2.053 (1.499)
Epoch: [12][180/200]	Time 0.355 (0.412)	Data 0.001 (0.054)	Loss 2.038 (1.528)
Epoch: [12][200/200]	Time 0.354 (0.414)	Data 0.001 (0.056)	Loss 2.218 (1.555)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.121 (0.214)	Data 0.000 (0.096)	
Extract Features: [100/128]	Time 0.118 (0.192)	Data 0.000 (0.075)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.653773069381714
==> Statistics for epoch 13: 1032 clusters
Epoch: [13][20/200]	Time 0.353 (0.410)	Data 0.001 (0.054)	Loss 0.409 (0.363)
Epoch: [13][40/200]	Time 0.355 (0.431)	Data 0.001 (0.070)	Loss 1.733 (0.611)
Epoch: [13][60/200]	Time 0.355 (0.406)	Data 0.000 (0.047)	Loss 1.500 (0.953)
Epoch: [13][80/200]	Time 0.359 (0.416)	Data 0.001 (0.057)	Loss 1.623 (1.114)
Epoch: [13][100/200]	Time 0.357 (0.421)	Data 0.001 (0.063)	Loss 1.635 (1.238)
Epoch: [13][120/200]	Time 0.356 (0.410)	Data 0.001 (0.053)	Loss 2.028 (1.331)
Epoch: [13][140/200]	Time 0.363 (0.414)	Data 0.001 (0.057)	Loss 1.794 (1.378)
Epoch: [13][160/200]	Time 0.356 (0.407)	Data 0.000 (0.050)	Loss 1.483 (1.431)
Epoch: [13][180/200]	Time 0.352 (0.412)	Data 0.001 (0.053)	Loss 1.970 (1.461)
Epoch: [13][200/200]	Time 0.358 (0.414)	Data 0.001 (0.056)	Loss 1.688 (1.481)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.503 (0.216)	Data 0.388 (0.101)	
Extract Features: [100/128]	Time 0.116 (0.200)	Data 0.000 (0.083)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.427942752838135
==> Statistics for epoch 14: 1002 clusters
Epoch: [14][20/200]	Time 0.354 (0.411)	Data 0.001 (0.052)	Loss 0.440 (0.376)
Epoch: [14][40/200]	Time 0.354 (0.429)	Data 0.001 (0.072)	Loss 1.438 (0.660)
Epoch: [14][60/200]	Time 0.353 (0.405)	Data 0.000 (0.048)	Loss 1.664 (1.003)
Epoch: [14][80/200]	Time 0.359 (0.414)	Data 0.001 (0.057)	Loss 1.575 (1.181)
Epoch: [14][100/200]	Time 0.359 (0.422)	Data 0.001 (0.063)	Loss 1.400 (1.297)
Epoch: [14][120/200]	Time 0.354 (0.411)	Data 0.000 (0.053)	Loss 1.386 (1.350)
Epoch: [14][140/200]	Time 0.358 (0.416)	Data 0.001 (0.057)	Loss 1.792 (1.422)
Epoch: [14][160/200]	Time 0.359 (0.419)	Data 0.001 (0.061)	Loss 1.621 (1.457)
Epoch: [14][180/200]	Time 0.359 (0.413)	Data 0.000 (0.054)	Loss 1.673 (1.486)
Epoch: [14][200/200]	Time 0.361 (0.416)	Data 0.001 (0.058)	Loss 2.137 (1.505)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.116 (0.213)	Data 0.000 (0.095)	
Extract Features: [100/128]	Time 0.113 (0.192)	Data 0.000 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.39167785644531
==> Statistics for epoch 15: 1003 clusters
Epoch: [15][20/200]	Time 0.358 (0.408)	Data 0.001 (0.050)	Loss 0.355 (0.379)
Epoch: [15][40/200]	Time 0.366 (0.425)	Data 0.001 (0.067)	Loss 1.509 (0.686)
Epoch: [15][60/200]	Time 0.355 (0.402)	Data 0.000 (0.045)	Loss 1.345 (0.996)
Epoch: [15][80/200]	Time 0.359 (0.410)	Data 0.001 (0.053)	Loss 1.685 (1.151)
Epoch: [15][100/200]	Time 0.353 (0.417)	Data 0.001 (0.060)	Loss 1.490 (1.257)
Epoch: [15][120/200]	Time 0.354 (0.407)	Data 0.000 (0.050)	Loss 1.441 (1.331)
Epoch: [15][140/200]	Time 0.356 (0.412)	Data 0.001 (0.055)	Loss 1.611 (1.383)
Epoch: [15][160/200]	Time 0.358 (0.416)	Data 0.001 (0.059)	Loss 1.500 (1.402)
Epoch: [15][180/200]	Time 0.358 (0.410)	Data 0.000 (0.052)	Loss 1.836 (1.429)
Epoch: [15][200/200]	Time 0.357 (0.413)	Data 0.000 (0.055)	Loss 1.489 (1.448)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.211)	Data 0.000 (0.093)	
Extract Features: [100/128]	Time 0.116 (0.193)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.46584105491638
==> Statistics for epoch 16: 1008 clusters
Epoch: [16][20/200]	Time 0.357 (0.408)	Data 0.001 (0.050)	Loss 0.566 (0.346)
Epoch: [16][40/200]	Time 0.355 (0.429)	Data 0.001 (0.069)	Loss 2.141 (0.658)
Epoch: [16][60/200]	Time 0.353 (0.405)	Data 0.000 (0.046)	Loss 1.395 (0.972)
Epoch: [16][80/200]	Time 0.354 (0.414)	Data 0.001 (0.056)	Loss 1.369 (1.136)
Epoch: [16][100/200]	Time 0.357 (0.418)	Data 0.001 (0.061)	Loss 2.013 (1.223)
Epoch: [16][120/200]	Time 0.351 (0.408)	Data 0.000 (0.051)	Loss 2.007 (1.297)
Epoch: [16][140/200]	Time 0.356 (0.412)	Data 0.001 (0.054)	Loss 1.644 (1.348)
Epoch: [16][160/200]	Time 0.353 (0.415)	Data 0.001 (0.058)	Loss 1.970 (1.380)
Epoch: [16][180/200]	Time 0.355 (0.409)	Data 0.000 (0.052)	Loss 2.165 (1.410)
Epoch: [16][200/200]	Time 0.355 (0.413)	Data 0.001 (0.055)	Loss 1.609 (1.429)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.210)	Data 0.000 (0.095)	
Extract Features: [100/128]	Time 0.128 (0.192)	Data 0.000 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.837238073349
==> Statistics for epoch 17: 1015 clusters
Epoch: [17][20/200]	Time 0.368 (0.415)	Data 0.001 (0.057)	Loss 0.346 (0.366)
Epoch: [17][40/200]	Time 0.361 (0.426)	Data 0.001 (0.069)	Loss 2.224 (0.668)
Epoch: [17][60/200]	Time 0.353 (0.402)	Data 0.000 (0.046)	Loss 1.104 (0.957)
Epoch: [17][80/200]	Time 0.354 (0.413)	Data 0.001 (0.057)	Loss 0.904 (1.135)
Epoch: [17][100/200]	Time 0.358 (0.418)	Data 0.001 (0.062)	Loss 1.497 (1.225)
Epoch: [17][120/200]	Time 0.356 (0.408)	Data 0.000 (0.051)	Loss 1.485 (1.286)
Epoch: [17][140/200]	Time 0.357 (0.414)	Data 0.001 (0.056)	Loss 1.439 (1.331)
Epoch: [17][160/200]	Time 0.353 (0.418)	Data 0.001 (0.061)	Loss 1.663 (1.367)
Epoch: [17][180/200]	Time 0.356 (0.411)	Data 0.000 (0.054)	Loss 1.693 (1.387)
Epoch: [17][200/200]	Time 0.357 (0.414)	Data 0.001 (0.056)	Loss 1.956 (1.410)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.114 (0.212)	Data 0.000 (0.095)	
Extract Features: [100/128]	Time 0.113 (0.192)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.60240697860718
==> Statistics for epoch 18: 994 clusters
Epoch: [18][20/200]	Time 0.352 (0.406)	Data 0.001 (0.050)	Loss 0.383 (0.342)
Epoch: [18][40/200]	Time 0.356 (0.421)	Data 0.001 (0.066)	Loss 2.562 (0.642)
Epoch: [18][60/200]	Time 0.352 (0.399)	Data 0.000 (0.044)	Loss 1.393 (0.963)
Epoch: [18][80/200]	Time 0.363 (0.409)	Data 0.001 (0.053)	Loss 2.089 (1.119)
Epoch: [18][100/200]	Time 0.354 (0.416)	Data 0.001 (0.059)	Loss 1.242 (1.233)
Epoch: [18][120/200]	Time 0.354 (0.406)	Data 0.000 (0.050)	Loss 1.417 (1.309)
Epoch: [18][140/200]	Time 0.354 (0.411)	Data 0.001 (0.055)	Loss 1.991 (1.358)
Epoch: [18][160/200]	Time 0.353 (0.415)	Data 0.001 (0.058)	Loss 1.619 (1.400)
Epoch: [18][180/200]	Time 0.353 (0.409)	Data 0.000 (0.052)	Loss 1.865 (1.421)
Epoch: [18][200/200]	Time 0.357 (0.412)	Data 0.001 (0.055)	Loss 1.420 (1.437)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.224 (0.208)	Data 0.111 (0.091)	
Extract Features: [100/128]	Time 0.114 (0.190)	Data 0.000 (0.072)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.933310747146606
==> Statistics for epoch 19: 1012 clusters
Epoch: [19][20/200]	Time 0.354 (0.406)	Data 0.001 (0.049)	Loss 0.521 (0.393)
Epoch: [19][40/200]	Time 0.358 (0.425)	Data 0.001 (0.068)	Loss 1.395 (0.622)
Epoch: [19][60/200]	Time 0.355 (0.402)	Data 0.000 (0.046)	Loss 1.705 (0.968)
Epoch: [19][80/200]	Time 0.360 (0.412)	Data 0.001 (0.056)	Loss 1.635 (1.112)
Epoch: [19][100/200]	Time 0.358 (0.417)	Data 0.001 (0.060)	Loss 2.217 (1.212)
Epoch: [19][120/200]	Time 0.354 (0.407)	Data 0.000 (0.050)	Loss 1.399 (1.285)
Epoch: [19][140/200]	Time 0.354 (0.413)	Data 0.001 (0.055)	Loss 1.324 (1.327)
Epoch: [19][160/200]	Time 0.364 (0.417)	Data 0.001 (0.059)	Loss 1.253 (1.345)
Epoch: [19][180/200]	Time 0.358 (0.410)	Data 0.000 (0.053)	Loss 1.506 (1.366)
Epoch: [19][200/200]	Time 0.357 (0.413)	Data 0.001 (0.055)	Loss 1.642 (1.386)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.218)	Data 0.000 (0.100)	
Extract Features: [100/128]	Time 0.116 (0.194)	Data 0.000 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.3430814743042
==> Statistics for epoch 20: 1039 clusters
Epoch: [20][20/200]	Time 0.353 (0.407)	Data 0.001 (0.051)	Loss 0.327 (0.352)
Epoch: [20][40/200]	Time 0.354 (0.427)	Data 0.001 (0.068)	Loss 2.039 (0.603)
Epoch: [20][60/200]	Time 0.349 (0.403)	Data 0.000 (0.045)	Loss 1.414 (0.932)
Epoch: [20][80/200]	Time 0.360 (0.410)	Data 0.001 (0.054)	Loss 1.748 (1.135)
Epoch: [20][100/200]	Time 0.354 (0.416)	Data 0.001 (0.059)	Loss 1.456 (1.230)
Epoch: [20][120/200]	Time 0.359 (0.406)	Data 0.001 (0.050)	Loss 1.132 (1.283)
Epoch: [20][140/200]	Time 0.358 (0.411)	Data 0.001 (0.054)	Loss 1.072 (1.324)
Epoch: [20][160/200]	Time 0.356 (0.404)	Data 0.001 (0.047)	Loss 1.545 (1.365)
Epoch: [20][180/200]	Time 0.356 (0.408)	Data 0.001 (0.051)	Loss 1.558 (1.399)
Epoch: [20][200/200]	Time 0.352 (0.413)	Data 0.001 (0.055)	Loss 1.630 (1.424)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.114 (0.211)	Data 0.000 (0.096)	
Extract Features: [100/128]	Time 0.168 (0.191)	Data 0.053 (0.075)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.86463451385498
==> Statistics for epoch 21: 1023 clusters
Epoch: [21][20/200]	Time 0.352 (0.410)	Data 0.001 (0.054)	Loss 0.282 (0.306)
Epoch: [21][40/200]	Time 0.350 (0.424)	Data 0.001 (0.068)	Loss 1.545 (0.594)
Epoch: [21][60/200]	Time 0.355 (0.401)	Data 0.000 (0.046)	Loss 1.415 (0.894)
Epoch: [21][80/200]	Time 0.360 (0.412)	Data 0.001 (0.057)	Loss 1.713 (1.074)
Epoch: [21][100/200]	Time 0.357 (0.418)	Data 0.001 (0.063)	Loss 1.421 (1.198)
Epoch: [21][120/200]	Time 0.356 (0.409)	Data 0.000 (0.052)	Loss 1.496 (1.280)
Epoch: [21][140/200]	Time 0.356 (0.414)	Data 0.001 (0.057)	Loss 1.712 (1.322)
Epoch: [21][160/200]	Time 0.357 (0.418)	Data 0.001 (0.061)	Loss 1.874 (1.363)
Epoch: [21][180/200]	Time 0.358 (0.411)	Data 0.000 (0.054)	Loss 1.666 (1.400)
Epoch: [21][200/200]	Time 0.357 (0.415)	Data 0.001 (0.057)	Loss 1.620 (1.426)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.154 (0.211)	Data 0.038 (0.094)	
Extract Features: [100/128]	Time 0.115 (0.193)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.0738959312439
==> Statistics for epoch 22: 1027 clusters
Epoch: [22][20/200]	Time 0.353 (0.404)	Data 0.001 (0.050)	Loss 0.212 (0.316)
Epoch: [22][40/200]	Time 0.362 (0.424)	Data 0.001 (0.068)	Loss 1.757 (0.574)
Epoch: [22][60/200]	Time 0.357 (0.403)	Data 0.000 (0.045)	Loss 1.728 (0.927)
Epoch: [22][80/200]	Time 0.355 (0.413)	Data 0.001 (0.055)	Loss 1.834 (1.110)
Epoch: [22][100/200]	Time 0.355 (0.418)	Data 0.001 (0.061)	Loss 1.802 (1.210)
Epoch: [22][120/200]	Time 0.360 (0.408)	Data 0.001 (0.051)	Loss 1.664 (1.292)
Epoch: [22][140/200]	Time 0.355 (0.412)	Data 0.001 (0.055)	Loss 1.888 (1.335)
Epoch: [22][160/200]	Time 0.354 (0.405)	Data 0.000 (0.048)	Loss 1.980 (1.379)
Epoch: [22][180/200]	Time 0.357 (0.408)	Data 0.001 (0.051)	Loss 1.559 (1.406)
Epoch: [22][200/200]	Time 0.361 (0.412)	Data 0.001 (0.054)	Loss 1.734 (1.427)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.114 (0.215)	Data 0.000 (0.100)	
Extract Features: [100/128]	Time 0.115 (0.194)	Data 0.000 (0.078)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.23890662193298
==> Statistics for epoch 23: 1025 clusters
Epoch: [23][20/200]	Time 0.354 (0.412)	Data 0.001 (0.056)	Loss 0.161 (0.331)
Epoch: [23][40/200]	Time 0.354 (0.428)	Data 0.001 (0.072)	Loss 1.717 (0.550)
Epoch: [23][60/200]	Time 0.354 (0.404)	Data 0.000 (0.048)	Loss 2.031 (0.921)
Epoch: [23][80/200]	Time 0.356 (0.414)	Data 0.001 (0.057)	Loss 2.112 (1.107)
Epoch: [23][100/200]	Time 0.359 (0.420)	Data 0.001 (0.063)	Loss 1.577 (1.221)
Epoch: [23][120/200]	Time 0.358 (0.411)	Data 0.001 (0.053)	Loss 1.651 (1.280)
Epoch: [23][140/200]	Time 0.359 (0.415)	Data 0.001 (0.057)	Loss 1.734 (1.342)
Epoch: [23][160/200]	Time 0.358 (0.408)	Data 0.000 (0.050)	Loss 2.136 (1.375)
Epoch: [23][180/200]	Time 0.373 (0.412)	Data 0.001 (0.054)	Loss 1.485 (1.398)
Epoch: [23][200/200]	Time 0.370 (0.415)	Data 0.001 (0.057)	Loss 1.437 (1.434)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.116 (0.215)	Data 0.001 (0.097)	
Extract Features: [100/128]	Time 0.117 (0.193)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.115312814712524
==> Statistics for epoch 24: 1040 clusters
Epoch: [24][20/200]	Time 0.354 (0.417)	Data 0.001 (0.052)	Loss 0.284 (0.306)
Epoch: [24][40/200]	Time 0.360 (0.427)	Data 0.001 (0.066)	Loss 1.867 (0.556)
Epoch: [24][60/200]	Time 0.354 (0.403)	Data 0.000 (0.044)	Loss 1.684 (0.887)
Epoch: [24][80/200]	Time 0.353 (0.411)	Data 0.001 (0.053)	Loss 1.918 (1.068)
Epoch: [24][100/200]	Time 0.355 (0.417)	Data 0.001 (0.059)	Loss 2.124 (1.182)
Epoch: [24][120/200]	Time 0.357 (0.408)	Data 0.001 (0.050)	Loss 1.717 (1.280)
Epoch: [24][140/200]	Time 0.357 (0.412)	Data 0.001 (0.055)	Loss 1.920 (1.320)
Epoch: [24][160/200]	Time 0.355 (0.405)	Data 0.000 (0.048)	Loss 1.784 (1.370)
Epoch: [24][180/200]	Time 0.356 (0.410)	Data 0.001 (0.052)	Loss 1.764 (1.407)
Epoch: [24][200/200]	Time 0.358 (0.413)	Data 0.001 (0.055)	Loss 1.633 (1.434)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.114 (0.214)	Data 0.000 (0.100)	
Extract Features: [100/128]	Time 0.115 (0.193)	Data 0.000 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.88101005554199
==> Statistics for epoch 25: 1039 clusters
Epoch: [25][20/200]	Time 0.350 (0.409)	Data 0.001 (0.053)	Loss 0.445 (0.311)
Epoch: [25][40/200]	Time 0.356 (0.424)	Data 0.001 (0.069)	Loss 1.858 (0.595)
Epoch: [25][60/200]	Time 0.351 (0.404)	Data 0.000 (0.046)	Loss 1.727 (0.904)
Epoch: [25][80/200]	Time 0.359 (0.413)	Data 0.001 (0.056)	Loss 1.887 (1.083)
Epoch: [25][100/200]	Time 0.352 (0.418)	Data 0.001 (0.060)	Loss 1.630 (1.214)
Epoch: [25][120/200]	Time 0.355 (0.408)	Data 0.001 (0.051)	Loss 1.402 (1.284)
Epoch: [25][140/200]	Time 0.359 (0.413)	Data 0.001 (0.056)	Loss 1.003 (1.330)
Epoch: [25][160/200]	Time 0.353 (0.406)	Data 0.000 (0.049)	Loss 1.044 (1.368)
Epoch: [25][180/200]	Time 0.356 (0.411)	Data 0.001 (0.053)	Loss 1.581 (1.400)
Epoch: [25][200/200]	Time 0.360 (0.414)	Data 0.001 (0.057)	Loss 1.425 (1.423)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.212)	Data 0.000 (0.095)	
Extract Features: [100/128]	Time 0.132 (0.194)	Data 0.000 (0.078)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.90374231338501
==> Statistics for epoch 26: 1032 clusters
Epoch: [26][20/200]	Time 0.354 (0.415)	Data 0.001 (0.058)	Loss 0.301 (0.338)
Epoch: [26][40/200]	Time 0.355 (0.426)	Data 0.001 (0.069)	Loss 1.909 (0.600)
Epoch: [26][60/200]	Time 0.353 (0.403)	Data 0.000 (0.047)	Loss 1.193 (0.939)
Epoch: [26][80/200]	Time 0.354 (0.412)	Data 0.001 (0.056)	Loss 1.362 (1.105)
Epoch: [26][100/200]	Time 0.356 (0.417)	Data 0.000 (0.061)	Loss 1.849 (1.230)
Epoch: [26][120/200]	Time 0.360 (0.407)	Data 0.001 (0.051)	Loss 1.430 (1.294)
Epoch: [26][140/200]	Time 0.363 (0.412)	Data 0.001 (0.056)	Loss 1.806 (1.342)
Epoch: [26][160/200]	Time 0.354 (0.405)	Data 0.000 (0.049)	Loss 1.329 (1.381)
Epoch: [26][180/200]	Time 0.360 (0.409)	Data 0.001 (0.053)	Loss 1.781 (1.421)
Epoch: [26][200/200]	Time 0.375 (0.413)	Data 0.001 (0.056)	Loss 1.583 (1.438)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.216)	Data 0.000 (0.101)	
Extract Features: [100/128]	Time 0.117 (0.195)	Data 0.000 (0.078)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.29984092712402
==> Statistics for epoch 27: 1052 clusters
Epoch: [27][20/200]	Time 0.353 (0.411)	Data 0.001 (0.056)	Loss 0.321 (0.328)
Epoch: [27][40/200]	Time 0.364 (0.425)	Data 0.001 (0.070)	Loss 1.118 (0.540)
Epoch: [27][60/200]	Time 0.355 (0.402)	Data 0.000 (0.047)	Loss 1.535 (0.901)
Epoch: [27][80/200]	Time 0.355 (0.411)	Data 0.001 (0.055)	Loss 2.010 (1.078)
Epoch: [27][100/200]	Time 0.353 (0.417)	Data 0.001 (0.061)	Loss 2.000 (1.184)
Epoch: [27][120/200]	Time 0.356 (0.407)	Data 0.001 (0.051)	Loss 1.470 (1.262)
Epoch: [27][140/200]	Time 0.365 (0.414)	Data 0.001 (0.056)	Loss 1.572 (1.328)
Epoch: [27][160/200]	Time 0.354 (0.407)	Data 0.000 (0.049)	Loss 1.887 (1.380)
Epoch: [27][180/200]	Time 0.365 (0.411)	Data 0.001 (0.053)	Loss 1.734 (1.411)
Epoch: [27][200/200]	Time 0.354 (0.414)	Data 0.001 (0.057)	Loss 1.509 (1.439)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.216)	Data 0.000 (0.097)	
Extract Features: [100/128]	Time 0.120 (0.192)	Data 0.000 (0.075)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.97021412849426
==> Statistics for epoch 28: 1040 clusters
Epoch: [28][20/200]	Time 0.356 (0.413)	Data 0.001 (0.057)	Loss 0.306 (0.289)
Epoch: [28][40/200]	Time 0.357 (0.422)	Data 0.001 (0.066)	Loss 1.321 (0.552)
Epoch: [28][60/200]	Time 0.351 (0.399)	Data 0.000 (0.044)	Loss 1.675 (0.880)
Epoch: [28][80/200]	Time 0.354 (0.409)	Data 0.001 (0.054)	Loss 1.358 (1.077)
Epoch: [28][100/200]	Time 0.356 (0.415)	Data 0.001 (0.060)	Loss 1.790 (1.176)
Epoch: [28][120/200]	Time 0.359 (0.405)	Data 0.001 (0.050)	Loss 1.513 (1.242)
Epoch: [28][140/200]	Time 0.359 (0.410)	Data 0.001 (0.054)	Loss 1.363 (1.302)
Epoch: [28][160/200]	Time 0.353 (0.405)	Data 0.000 (0.048)	Loss 2.122 (1.339)
Epoch: [28][180/200]	Time 0.355 (0.408)	Data 0.001 (0.051)	Loss 1.631 (1.367)
Epoch: [28][200/200]	Time 0.358 (0.412)	Data 0.001 (0.055)	Loss 2.144 (1.402)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.116 (0.219)	Data 0.000 (0.104)	
Extract Features: [100/128]	Time 0.119 (0.194)	Data 0.000 (0.078)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.7014594078064
==> Statistics for epoch 29: 1036 clusters
Epoch: [29][20/200]	Time 0.355 (0.413)	Data 0.001 (0.057)	Loss 0.178 (0.335)
Epoch: [29][40/200]	Time 0.356 (0.428)	Data 0.001 (0.072)	Loss 1.956 (0.598)
Epoch: [29][60/200]	Time 0.354 (0.404)	Data 0.000 (0.048)	Loss 1.577 (0.920)
Epoch: [29][80/200]	Time 0.354 (0.415)	Data 0.001 (0.057)	Loss 1.586 (1.099)
Epoch: [29][100/200]	Time 0.363 (0.422)	Data 0.001 (0.063)	Loss 1.798 (1.200)
Epoch: [29][120/200]	Time 0.355 (0.411)	Data 0.001 (0.053)	Loss 1.704 (1.272)
Epoch: [29][140/200]	Time 0.357 (0.416)	Data 0.001 (0.058)	Loss 2.002 (1.347)
Epoch: [29][160/200]	Time 0.356 (0.409)	Data 0.000 (0.051)	Loss 1.843 (1.377)
Epoch: [29][180/200]	Time 0.355 (0.412)	Data 0.001 (0.055)	Loss 1.590 (1.408)
Epoch: [29][200/200]	Time 0.359 (0.416)	Data 0.001 (0.058)	Loss 1.909 (1.435)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.123 (0.208)	Data 0.001 (0.091)	
Extract Features: [100/128]	Time 0.117 (0.192)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.24938654899597
==> Statistics for epoch 30: 1034 clusters
Epoch: [30][20/200]	Time 0.358 (0.412)	Data 0.001 (0.056)	Loss 0.330 (0.325)
Epoch: [30][40/200]	Time 0.356 (0.423)	Data 0.001 (0.066)	Loss 1.216 (0.568)
Epoch: [30][60/200]	Time 0.349 (0.401)	Data 0.000 (0.044)	Loss 1.259 (0.898)
Epoch: [30][80/200]	Time 0.362 (0.410)	Data 0.001 (0.054)	Loss 1.908 (1.069)
Epoch: [30][100/200]	Time 0.360 (0.417)	Data 0.002 (0.061)	Loss 1.500 (1.194)
Epoch: [30][120/200]	Time 0.354 (0.407)	Data 0.001 (0.051)	Loss 1.518 (1.264)
Epoch: [30][140/200]	Time 0.359 (0.412)	Data 0.001 (0.055)	Loss 1.624 (1.317)
Epoch: [30][160/200]	Time 0.356 (0.406)	Data 0.000 (0.048)	Loss 2.106 (1.365)
Epoch: [30][180/200]	Time 0.356 (0.410)	Data 0.001 (0.053)	Loss 1.695 (1.400)
Epoch: [30][200/200]	Time 0.357 (0.413)	Data 0.001 (0.056)	Loss 1.645 (1.425)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.234 (0.207)	Data 0.119 (0.090)	
Extract Features: [100/128]	Time 0.115 (0.188)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.11573815345764
==> Statistics for epoch 31: 1031 clusters
Epoch: [31][20/200]	Time 0.359 (0.413)	Data 0.001 (0.057)	Loss 0.230 (0.308)
Epoch: [31][40/200]	Time 0.359 (0.428)	Data 0.001 (0.072)	Loss 1.448 (0.527)
Epoch: [31][60/200]	Time 0.354 (0.404)	Data 0.000 (0.048)	Loss 1.553 (0.906)
Epoch: [31][80/200]	Time 0.355 (0.413)	Data 0.001 (0.057)	Loss 1.675 (1.095)
Epoch: [31][100/200]	Time 0.355 (0.419)	Data 0.001 (0.062)	Loss 1.407 (1.217)
Epoch: [31][120/200]	Time 0.355 (0.409)	Data 0.001 (0.052)	Loss 1.602 (1.304)
Epoch: [31][140/200]	Time 0.355 (0.414)	Data 0.001 (0.057)	Loss 1.539 (1.345)
Epoch: [31][160/200]	Time 0.359 (0.408)	Data 0.000 (0.050)	Loss 1.868 (1.386)
Epoch: [31][180/200]	Time 0.358 (0.412)	Data 0.001 (0.055)	Loss 1.472 (1.411)
Epoch: [31][200/200]	Time 0.355 (0.416)	Data 0.001 (0.058)	Loss 1.409 (1.440)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.112 (0.217)	Data 0.000 (0.101)	
Extract Features: [100/128]	Time 0.117 (0.194)	Data 0.000 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.13667011260986
==> Statistics for epoch 32: 1039 clusters
Epoch: [32][20/200]	Time 0.352 (0.411)	Data 0.001 (0.054)	Loss 0.348 (0.331)
Epoch: [32][40/200]	Time 0.355 (0.428)	Data 0.000 (0.068)	Loss 1.806 (0.562)
Epoch: [32][60/200]	Time 0.355 (0.403)	Data 0.000 (0.046)	Loss 1.336 (0.903)
Epoch: [32][80/200]	Time 0.356 (0.411)	Data 0.001 (0.054)	Loss 1.606 (1.090)
Epoch: [32][100/200]	Time 0.354 (0.416)	Data 0.001 (0.060)	Loss 1.630 (1.181)
Epoch: [32][120/200]	Time 0.353 (0.406)	Data 0.001 (0.050)	Loss 1.726 (1.268)
Epoch: [32][140/200]	Time 0.355 (0.412)	Data 0.001 (0.055)	Loss 1.561 (1.323)
Epoch: [32][160/200]	Time 0.354 (0.405)	Data 0.000 (0.048)	Loss 1.734 (1.357)
Epoch: [32][180/200]	Time 0.355 (0.409)	Data 0.001 (0.052)	Loss 1.862 (1.395)
Epoch: [32][200/200]	Time 0.359 (0.413)	Data 0.001 (0.056)	Loss 1.270 (1.410)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.210)	Data 0.000 (0.096)	
Extract Features: [100/128]	Time 0.213 (0.190)	Data 0.098 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.38754320144653
==> Statistics for epoch 33: 1031 clusters
Epoch: [33][20/200]	Time 0.353 (0.408)	Data 0.001 (0.053)	Loss 0.200 (0.313)
Epoch: [33][40/200]	Time 0.366 (0.425)	Data 0.002 (0.070)	Loss 1.787 (0.566)
Epoch: [33][60/200]	Time 0.350 (0.402)	Data 0.000 (0.047)	Loss 1.782 (0.910)
Epoch: [33][80/200]	Time 0.355 (0.411)	Data 0.001 (0.056)	Loss 1.778 (1.072)
Epoch: [33][100/200]	Time 0.357 (0.417)	Data 0.001 (0.061)	Loss 1.319 (1.185)
Epoch: [33][120/200]	Time 0.361 (0.408)	Data 0.001 (0.051)	Loss 1.297 (1.270)
Epoch: [33][140/200]	Time 0.357 (0.413)	Data 0.001 (0.056)	Loss 1.535 (1.307)
Epoch: [33][160/200]	Time 0.354 (0.406)	Data 0.000 (0.049)	Loss 1.131 (1.351)
Epoch: [33][180/200]	Time 0.357 (0.411)	Data 0.001 (0.054)	Loss 1.859 (1.381)
Epoch: [33][200/200]	Time 0.361 (0.414)	Data 0.001 (0.057)	Loss 1.620 (1.403)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.392 (0.214)	Data 0.271 (0.095)	
Extract Features: [100/128]	Time 0.115 (0.194)	Data 0.000 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.042624950408936
==> Statistics for epoch 34: 1048 clusters
Epoch: [34][20/200]	Time 0.355 (0.407)	Data 0.001 (0.052)	Loss 0.264 (0.335)
Epoch: [34][40/200]	Time 0.363 (0.426)	Data 0.001 (0.069)	Loss 1.494 (0.552)
Epoch: [34][60/200]	Time 0.356 (0.405)	Data 0.000 (0.046)	Loss 1.813 (0.906)
Epoch: [34][80/200]	Time 0.361 (0.415)	Data 0.001 (0.057)	Loss 1.307 (1.080)
Epoch: [34][100/200]	Time 0.354 (0.421)	Data 0.001 (0.063)	Loss 1.615 (1.194)
Epoch: [34][120/200]	Time 0.355 (0.411)	Data 0.001 (0.053)	Loss 1.734 (1.281)
Epoch: [34][140/200]	Time 0.360 (0.415)	Data 0.001 (0.057)	Loss 1.630 (1.330)
Epoch: [34][160/200]	Time 0.352 (0.407)	Data 0.000 (0.050)	Loss 1.702 (1.367)
Epoch: [34][180/200]	Time 0.358 (0.412)	Data 0.001 (0.054)	Loss 1.530 (1.402)
Epoch: [34][200/200]	Time 0.361 (0.415)	Data 0.001 (0.057)	Loss 1.467 (1.433)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.179 (0.208)	Data 0.064 (0.093)	
Extract Features: [100/128]	Time 0.122 (0.190)	Data 0.007 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.60373401641846
==> Statistics for epoch 35: 1041 clusters
Epoch: [35][20/200]	Time 0.353 (0.406)	Data 0.001 (0.051)	Loss 0.301 (0.320)
Epoch: [35][40/200]	Time 0.353 (0.424)	Data 0.001 (0.069)	Loss 1.687 (0.574)
Epoch: [35][60/200]	Time 0.357 (0.401)	Data 0.000 (0.046)	Loss 1.729 (0.886)
Epoch: [35][80/200]	Time 0.357 (0.413)	Data 0.001 (0.057)	Loss 1.722 (1.072)
Epoch: [35][100/200]	Time 0.354 (0.420)	Data 0.001 (0.064)	Loss 1.615 (1.193)
Epoch: [35][120/200]	Time 0.354 (0.409)	Data 0.001 (0.053)	Loss 1.771 (1.268)
Epoch: [35][140/200]	Time 0.358 (0.414)	Data 0.001 (0.058)	Loss 1.458 (1.324)
Epoch: [35][160/200]	Time 0.358 (0.407)	Data 0.000 (0.050)	Loss 1.802 (1.359)
Epoch: [35][180/200]	Time 0.355 (0.411)	Data 0.001 (0.055)	Loss 1.899 (1.387)
Epoch: [35][200/200]	Time 0.362 (0.415)	Data 0.001 (0.058)	Loss 1.501 (1.417)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.306 (0.210)	Data 0.192 (0.093)	
Extract Features: [100/128]	Time 0.116 (0.191)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.22924494743347
==> Statistics for epoch 36: 1039 clusters
Epoch: [36][20/200]	Time 0.356 (0.409)	Data 0.001 (0.053)	Loss 0.286 (0.291)
Epoch: [36][40/200]	Time 0.352 (0.423)	Data 0.001 (0.069)	Loss 1.207 (0.544)
Epoch: [36][60/200]	Time 0.350 (0.401)	Data 0.000 (0.046)	Loss 1.630 (0.897)
Epoch: [36][80/200]	Time 0.358 (0.410)	Data 0.001 (0.055)	Loss 2.000 (1.079)
Epoch: [36][100/200]	Time 0.355 (0.416)	Data 0.001 (0.060)	Loss 1.932 (1.180)
Epoch: [36][120/200]	Time 0.354 (0.406)	Data 0.001 (0.050)	Loss 1.620 (1.256)
Epoch: [36][140/200]	Time 0.358 (0.414)	Data 0.001 (0.057)	Loss 1.386 (1.303)
Epoch: [36][160/200]	Time 0.353 (0.407)	Data 0.000 (0.050)	Loss 1.723 (1.349)
Epoch: [36][180/200]	Time 0.358 (0.411)	Data 0.001 (0.054)	Loss 1.941 (1.387)
Epoch: [36][200/200]	Time 0.362 (0.414)	Data 0.001 (0.057)	Loss 1.173 (1.404)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.116 (0.212)	Data 0.000 (0.095)	
Extract Features: [100/128]	Time 0.117 (0.193)	Data 0.000 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.00283980369568
==> Statistics for epoch 37: 1050 clusters
Epoch: [37][20/200]	Time 0.356 (0.414)	Data 0.001 (0.056)	Loss 0.412 (0.308)
Epoch: [37][40/200]	Time 0.351 (0.426)	Data 0.001 (0.070)	Loss 1.702 (0.548)
Epoch: [37][60/200]	Time 0.356 (0.403)	Data 0.000 (0.047)	Loss 1.487 (0.871)
Epoch: [37][80/200]	Time 0.355 (0.412)	Data 0.001 (0.056)	Loss 1.318 (1.024)
Epoch: [37][100/200]	Time 0.356 (0.418)	Data 0.001 (0.062)	Loss 1.361 (1.160)
Epoch: [37][120/200]	Time 0.356 (0.408)	Data 0.001 (0.052)	Loss 1.510 (1.244)
Epoch: [37][140/200]	Time 0.356 (0.414)	Data 0.001 (0.056)	Loss 2.055 (1.304)
Epoch: [37][160/200]	Time 0.358 (0.407)	Data 0.000 (0.049)	Loss 1.238 (1.349)
Epoch: [37][180/200]	Time 0.355 (0.411)	Data 0.001 (0.054)	Loss 1.611 (1.375)
Epoch: [37][200/200]	Time 0.358 (0.415)	Data 0.001 (0.057)	Loss 1.915 (1.403)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.114 (0.214)	Data 0.000 (0.096)	
Extract Features: [100/128]	Time 0.118 (0.195)	Data 0.000 (0.078)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.4987850189209
==> Statistics for epoch 38: 1041 clusters
Epoch: [38][20/200]	Time 0.352 (0.409)	Data 0.001 (0.055)	Loss 0.225 (0.314)
Epoch: [38][40/200]	Time 0.353 (0.425)	Data 0.000 (0.071)	Loss 1.503 (0.569)
Epoch: [38][60/200]	Time 0.354 (0.401)	Data 0.000 (0.047)	Loss 1.659 (0.899)
Epoch: [38][80/200]	Time 0.355 (0.411)	Data 0.001 (0.057)	Loss 1.789 (1.068)
Epoch: [38][100/200]	Time 0.352 (0.416)	Data 0.001 (0.062)	Loss 1.385 (1.185)
Epoch: [38][120/200]	Time 0.359 (0.406)	Data 0.001 (0.051)	Loss 1.637 (1.252)
Epoch: [38][140/200]	Time 0.357 (0.411)	Data 0.001 (0.056)	Loss 1.369 (1.301)
Epoch: [38][160/200]	Time 0.353 (0.405)	Data 0.000 (0.049)	Loss 1.586 (1.335)
Epoch: [38][180/200]	Time 0.355 (0.408)	Data 0.001 (0.053)	Loss 1.876 (1.370)
Epoch: [38][200/200]	Time 0.363 (0.411)	Data 0.001 (0.056)	Loss 1.329 (1.397)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.266 (0.214)	Data 0.154 (0.096)	
Extract Features: [100/128]	Time 0.116 (0.195)	Data 0.000 (0.079)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.98169469833374
==> Statistics for epoch 39: 1033 clusters
Epoch: [39][20/200]	Time 0.360 (0.413)	Data 0.001 (0.057)	Loss 0.238 (0.276)
Epoch: [39][40/200]	Time 0.358 (0.424)	Data 0.001 (0.068)	Loss 1.491 (0.547)
Epoch: [39][60/200]	Time 0.352 (0.401)	Data 0.000 (0.045)	Loss 1.338 (0.890)
Epoch: [39][80/200]	Time 0.359 (0.412)	Data 0.001 (0.055)	Loss 1.415 (1.061)
Epoch: [39][100/200]	Time 0.366 (0.418)	Data 0.001 (0.061)	Loss 1.379 (1.157)
Epoch: [39][120/200]	Time 0.363 (0.408)	Data 0.001 (0.051)	Loss 2.042 (1.229)
Epoch: [39][140/200]	Time 0.358 (0.413)	Data 0.001 (0.056)	Loss 1.351 (1.275)
Epoch: [39][160/200]	Time 0.353 (0.406)	Data 0.000 (0.049)	Loss 1.587 (1.313)
Epoch: [39][180/200]	Time 0.365 (0.410)	Data 0.001 (0.052)	Loss 1.531 (1.351)
Epoch: [39][200/200]	Time 0.358 (0.414)	Data 0.001 (0.056)	Loss 1.723 (1.367)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.345 (0.212)	Data 0.229 (0.096)	
Extract Features: [100/128]	Time 0.121 (0.192)	Data 0.000 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.09660744667053
==> Statistics for epoch 40: 1035 clusters
Epoch: [40][20/200]	Time 0.357 (0.413)	Data 0.001 (0.057)	Loss 0.248 (0.286)
Epoch: [40][40/200]	Time 0.351 (0.424)	Data 0.001 (0.068)	Loss 1.799 (0.529)
Epoch: [40][60/200]	Time 0.349 (0.401)	Data 0.000 (0.046)	Loss 1.402 (0.869)
Epoch: [40][80/200]	Time 0.357 (0.409)	Data 0.000 (0.053)	Loss 1.769 (1.043)
Epoch: [40][100/200]	Time 0.356 (0.415)	Data 0.001 (0.059)	Loss 1.551 (1.157)
Epoch: [40][120/200]	Time 0.358 (0.407)	Data 0.001 (0.049)	Loss 1.257 (1.235)
Epoch: [40][140/200]	Time 0.358 (0.412)	Data 0.001 (0.055)	Loss 1.482 (1.290)
Epoch: [40][160/200]	Time 0.353 (0.405)	Data 0.000 (0.048)	Loss 1.803 (1.327)
Epoch: [40][180/200]	Time 0.361 (0.409)	Data 0.001 (0.052)	Loss 2.028 (1.355)
Epoch: [40][200/200]	Time 0.355 (0.412)	Data 0.000 (0.055)	Loss 1.492 (1.381)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.280 (0.218)	Data 0.165 (0.101)	
Extract Features: [100/128]	Time 0.121 (0.199)	Data 0.000 (0.081)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.40143942832947
==> Statistics for epoch 41: 1052 clusters
Epoch: [41][20/200]	Time 0.360 (0.410)	Data 0.001 (0.052)	Loss 0.312 (0.287)
Epoch: [41][40/200]	Time 0.358 (0.427)	Data 0.001 (0.070)	Loss 1.739 (0.552)
Epoch: [41][60/200]	Time 0.355 (0.404)	Data 0.000 (0.047)	Loss 1.448 (0.887)
Epoch: [41][80/200]	Time 0.360 (0.415)	Data 0.001 (0.058)	Loss 1.606 (1.065)
Epoch: [41][100/200]	Time 0.354 (0.422)	Data 0.001 (0.064)	Loss 1.608 (1.174)
Epoch: [41][120/200]	Time 0.356 (0.412)	Data 0.001 (0.054)	Loss 1.578 (1.253)
Epoch: [41][140/200]	Time 0.356 (0.417)	Data 0.000 (0.058)	Loss 1.486 (1.297)
Epoch: [41][160/200]	Time 0.354 (0.409)	Data 0.000 (0.051)	Loss 1.684 (1.338)
Epoch: [41][180/200]	Time 0.371 (0.413)	Data 0.001 (0.055)	Loss 2.269 (1.371)
Epoch: [41][200/200]	Time 0.358 (0.416)	Data 0.001 (0.057)	Loss 1.459 (1.400)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.114 (0.211)	Data 0.000 (0.092)	
Extract Features: [100/128]	Time 0.129 (0.194)	Data 0.000 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.91018009185791
==> Statistics for epoch 42: 1042 clusters
Epoch: [42][20/200]	Time 0.357 (0.409)	Data 0.001 (0.054)	Loss 0.222 (0.307)
Epoch: [42][40/200]	Time 0.350 (0.421)	Data 0.000 (0.066)	Loss 1.526 (0.565)
Epoch: [42][60/200]	Time 0.354 (0.399)	Data 0.000 (0.044)	Loss 1.368 (0.888)
Epoch: [42][80/200]	Time 0.354 (0.407)	Data 0.001 (0.053)	Loss 1.542 (1.074)
Epoch: [42][100/200]	Time 0.354 (0.412)	Data 0.001 (0.058)	Loss 1.507 (1.174)
Epoch: [42][120/200]	Time 0.353 (0.403)	Data 0.001 (0.048)	Loss 1.297 (1.238)
Epoch: [42][140/200]	Time 0.353 (0.409)	Data 0.000 (0.054)	Loss 2.147 (1.281)
Epoch: [42][160/200]	Time 0.352 (0.402)	Data 0.000 (0.047)	Loss 1.667 (1.312)
Epoch: [42][180/200]	Time 0.350 (0.407)	Data 0.001 (0.052)	Loss 1.781 (1.349)
Epoch: [42][200/200]	Time 0.356 (0.411)	Data 0.001 (0.056)	Loss 2.191 (1.385)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.206)	Data 0.000 (0.089)	
Extract Features: [100/128]	Time 0.117 (0.191)	Data 0.000 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.96956491470337
==> Statistics for epoch 43: 1030 clusters
Epoch: [43][20/200]	Time 0.356 (0.412)	Data 0.001 (0.056)	Loss 0.266 (0.316)
Epoch: [43][40/200]	Time 0.353 (0.426)	Data 0.001 (0.070)	Loss 1.470 (0.590)
Epoch: [43][60/200]	Time 0.351 (0.403)	Data 0.000 (0.047)	Loss 1.804 (0.903)
Epoch: [43][80/200]	Time 0.357 (0.413)	Data 0.001 (0.057)	Loss 1.426 (1.086)
Epoch: [43][100/200]	Time 0.352 (0.420)	Data 0.001 (0.063)	Loss 1.921 (1.192)
Epoch: [43][120/200]	Time 0.359 (0.410)	Data 0.001 (0.053)	Loss 1.496 (1.258)
Epoch: [43][140/200]	Time 0.358 (0.414)	Data 0.001 (0.057)	Loss 1.600 (1.322)
Epoch: [43][160/200]	Time 0.357 (0.407)	Data 0.000 (0.050)	Loss 1.742 (1.355)
Epoch: [43][180/200]	Time 0.353 (0.411)	Data 0.000 (0.054)	Loss 1.670 (1.384)
Epoch: [43][200/200]	Time 0.360 (0.415)	Data 0.001 (0.058)	Loss 1.850 (1.408)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.114 (0.208)	Data 0.000 (0.091)	
Extract Features: [100/128]	Time 0.116 (0.194)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.869603395462036
==> Statistics for epoch 44: 1033 clusters
Epoch: [44][20/200]	Time 0.352 (0.410)	Data 0.001 (0.052)	Loss 0.313 (0.311)
Epoch: [44][40/200]	Time 0.355 (0.430)	Data 0.000 (0.072)	Loss 1.563 (0.542)
Epoch: [44][60/200]	Time 0.352 (0.405)	Data 0.000 (0.048)	Loss 1.391 (0.876)
Epoch: [44][80/200]	Time 0.355 (0.413)	Data 0.001 (0.056)	Loss 1.690 (1.037)
Epoch: [44][100/200]	Time 0.354 (0.418)	Data 0.000 (0.061)	Loss 2.155 (1.159)
Epoch: [44][120/200]	Time 0.358 (0.408)	Data 0.001 (0.051)	Loss 1.979 (1.225)
Epoch: [44][140/200]	Time 0.354 (0.412)	Data 0.001 (0.056)	Loss 1.535 (1.287)
Epoch: [44][160/200]	Time 0.351 (0.406)	Data 0.000 (0.049)	Loss 1.440 (1.322)
Epoch: [44][180/200]	Time 0.358 (0.409)	Data 0.001 (0.052)	Loss 1.526 (1.352)
Epoch: [44][200/200]	Time 0.353 (0.413)	Data 0.001 (0.055)	Loss 1.758 (1.381)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.395 (0.215)	Data 0.279 (0.097)	
Extract Features: [100/128]	Time 0.118 (0.194)	Data 0.000 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.317631244659424
==> Statistics for epoch 45: 1034 clusters
Epoch: [45][20/200]	Time 0.357 (0.408)	Data 0.001 (0.052)	Loss 0.354 (0.318)
Epoch: [45][40/200]	Time 0.354 (0.426)	Data 0.001 (0.067)	Loss 1.867 (0.548)
Epoch: [45][60/200]	Time 0.356 (0.403)	Data 0.000 (0.045)	Loss 1.819 (0.885)
Epoch: [45][80/200]	Time 0.356 (0.412)	Data 0.001 (0.054)	Loss 1.276 (1.065)
Epoch: [45][100/200]	Time 0.357 (0.417)	Data 0.001 (0.060)	Loss 1.554 (1.193)
Epoch: [45][120/200]	Time 0.352 (0.407)	Data 0.001 (0.050)	Loss 1.843 (1.263)
Epoch: [45][140/200]	Time 0.356 (0.411)	Data 0.001 (0.054)	Loss 1.536 (1.318)
Epoch: [45][160/200]	Time 0.351 (0.405)	Data 0.000 (0.047)	Loss 1.748 (1.356)
Epoch: [45][180/200]	Time 0.353 (0.408)	Data 0.001 (0.051)	Loss 1.902 (1.395)
Epoch: [45][200/200]	Time 0.361 (0.412)	Data 0.001 (0.054)	Loss 1.946 (1.422)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.168 (0.213)	Data 0.056 (0.098)	
Extract Features: [100/128]	Time 0.115 (0.195)	Data 0.000 (0.079)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.69351077079773
==> Statistics for epoch 46: 1033 clusters
Epoch: [46][20/200]	Time 0.357 (0.407)	Data 0.001 (0.050)	Loss 0.368 (0.308)
Epoch: [46][40/200]	Time 0.360 (0.426)	Data 0.001 (0.070)	Loss 1.755 (0.545)
Epoch: [46][60/200]	Time 0.354 (0.402)	Data 0.000 (0.047)	Loss 1.325 (0.867)
Epoch: [46][80/200]	Time 0.352 (0.415)	Data 0.001 (0.058)	Loss 2.058 (1.035)
Epoch: [46][100/200]	Time 0.360 (0.421)	Data 0.001 (0.064)	Loss 1.821 (1.155)
Epoch: [46][120/200]	Time 0.362 (0.411)	Data 0.001 (0.053)	Loss 1.194 (1.227)
Epoch: [46][140/200]	Time 0.360 (0.416)	Data 0.001 (0.058)	Loss 1.581 (1.277)
Epoch: [46][160/200]	Time 0.354 (0.409)	Data 0.000 (0.051)	Loss 1.383 (1.321)
Epoch: [46][180/200]	Time 0.361 (0.412)	Data 0.001 (0.055)	Loss 1.518 (1.349)
Epoch: [46][200/200]	Time 0.355 (0.415)	Data 0.000 (0.058)	Loss 1.396 (1.372)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.113 (0.217)	Data 0.000 (0.100)	
Extract Features: [100/128]	Time 0.115 (0.194)	Data 0.000 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.888432264328
==> Statistics for epoch 47: 1051 clusters
Epoch: [47][20/200]	Time 0.359 (0.405)	Data 0.001 (0.049)	Loss 0.189 (0.289)
Epoch: [47][40/200]	Time 0.358 (0.423)	Data 0.001 (0.067)	Loss 1.632 (0.511)
Epoch: [47][60/200]	Time 0.355 (0.403)	Data 0.000 (0.045)	Loss 1.401 (0.839)
Epoch: [47][80/200]	Time 0.354 (0.412)	Data 0.001 (0.056)	Loss 1.459 (1.044)
Epoch: [47][100/200]	Time 0.354 (0.417)	Data 0.001 (0.061)	Loss 1.997 (1.153)
Epoch: [47][120/200]	Time 0.355 (0.407)	Data 0.001 (0.051)	Loss 1.769 (1.233)
Epoch: [47][140/200]	Time 0.359 (0.412)	Data 0.001 (0.056)	Loss 1.848 (1.290)
Epoch: [47][160/200]	Time 0.353 (0.405)	Data 0.000 (0.049)	Loss 1.310 (1.320)
Epoch: [47][180/200]	Time 0.356 (0.410)	Data 0.001 (0.054)	Loss 1.409 (1.343)
Epoch: [47][200/200]	Time 0.360 (0.414)	Data 0.001 (0.057)	Loss 1.597 (1.373)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.116 (0.213)	Data 0.000 (0.098)	
Extract Features: [100/128]	Time 0.114 (0.193)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.153605699539185
==> Statistics for epoch 48: 1044 clusters
Epoch: [48][20/200]	Time 0.353 (0.412)	Data 0.001 (0.054)	Loss 0.214 (0.299)
Epoch: [48][40/200]	Time 0.357 (0.426)	Data 0.001 (0.069)	Loss 1.727 (0.547)
Epoch: [48][60/200]	Time 0.352 (0.402)	Data 0.000 (0.046)	Loss 1.934 (0.885)
Epoch: [48][80/200]	Time 0.361 (0.412)	Data 0.001 (0.055)	Loss 1.364 (1.042)
Epoch: [48][100/200]	Time 0.357 (0.419)	Data 0.001 (0.062)	Loss 1.166 (1.152)
Epoch: [48][120/200]	Time 0.359 (0.408)	Data 0.001 (0.052)	Loss 2.123 (1.229)
Epoch: [48][140/200]	Time 0.356 (0.413)	Data 0.001 (0.057)	Loss 1.816 (1.293)
Epoch: [48][160/200]	Time 0.356 (0.407)	Data 0.000 (0.050)	Loss 1.861 (1.340)
Epoch: [48][180/200]	Time 0.363 (0.412)	Data 0.001 (0.054)	Loss 1.570 (1.369)
Epoch: [48][200/200]	Time 0.360 (0.414)	Data 0.001 (0.056)	Loss 1.624 (1.400)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.221 (0.215)	Data 0.108 (0.097)	
Extract Features: [100/128]	Time 0.115 (0.194)	Data 0.000 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.97649955749512
==> Statistics for epoch 49: 1034 clusters
Epoch: [49][20/200]	Time 0.355 (0.407)	Data 0.001 (0.052)	Loss 0.234 (0.292)
Epoch: [49][40/200]	Time 0.354 (0.421)	Data 0.000 (0.066)	Loss 1.576 (0.534)
Epoch: [49][60/200]	Time 0.356 (0.399)	Data 0.000 (0.044)	Loss 1.569 (0.872)
Epoch: [49][80/200]	Time 0.355 (0.411)	Data 0.001 (0.055)	Loss 1.629 (1.063)
Epoch: [49][100/200]	Time 0.356 (0.416)	Data 0.001 (0.060)	Loss 1.711 (1.167)
Epoch: [49][120/200]	Time 0.353 (0.406)	Data 0.000 (0.050)	Loss 1.715 (1.235)
Epoch: [49][140/200]	Time 0.361 (0.411)	Data 0.001 (0.055)	Loss 1.532 (1.281)
Epoch: [49][160/200]	Time 0.353 (0.404)	Data 0.000 (0.048)	Loss 1.770 (1.324)
Epoch: [49][180/200]	Time 0.359 (0.408)	Data 0.001 (0.052)	Loss 1.590 (1.355)
Epoch: [49][200/200]	Time 0.356 (0.412)	Data 0.000 (0.056)	Loss 1.623 (1.384)
Extract Features: [50/367]	Time 0.115 (0.214)	Data 0.000 (0.097)	
Extract Features: [100/367]	Time 0.116 (0.198)	Data 0.000 (0.081)	
Extract Features: [150/367]	Time 0.117 (0.193)	Data 0.000 (0.075)	
Extract Features: [200/367]	Time 0.117 (0.190)	Data 0.000 (0.072)	
Extract Features: [250/367]	Time 0.185 (0.189)	Data 0.000 (0.070)	
Extract Features: [300/367]	Time 0.347 (0.187)	Data 0.234 (0.069)	
Extract Features: [350/367]	Time 0.114 (0.185)	Data 0.000 (0.068)	
Mean AP: 52.5%

 * Finished epoch  49  model mAP: 52.5%  best: 52.5% *

==> Test with the best model:
=> Loaded checkpoint 'log/msmt17/resnet50_cion/model_best.pth.tar'
Extract Features: [50/367]	Time 0.408 (0.219)	Data 0.297 (0.102)	
Extract Features: [100/367]	Time 0.110 (0.201)	Data 0.000 (0.086)	
Extract Features: [150/367]	Time 0.374 (0.195)	Data 0.259 (0.078)	
Extract Features: [200/367]	Time 0.115 (0.193)	Data 0.000 (0.077)	
Extract Features: [250/367]	Time 0.116 (0.192)	Data 0.000 (0.075)	
Extract Features: [300/367]	Time 0.115 (0.191)	Data 0.000 (0.075)	
Extract Features: [350/367]	Time 0.114 (0.189)	Data 0.000 (0.073)	
Mean AP: 52.5%
CMC Scores:
  top-1          78.3%
  top-5          86.8%
  top-10         89.7%
Total running time:  2:38:56.062177
