==========
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='vit_tiny', pretrained_path='/home/ma-user/work/Projects/ReIDNets_Checkpoints_TransReID/ViT_Tiny_P16_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=True, 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/vit_tiny_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
  ----------------------------------------
Using convolution stem
using drop_out rate is : 0.0
using attn_drop_out rate is : 0.0
using drop_path rate is : 0.3
Convert dino model......
Load 172 / 177 layers.
ViT Tiny Created!
optimizer: SGD
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.911 (0.351)	Data 0.658 (0.128)	
Extract Features: [100/128]	Time 0.068 (0.259)	Data 0.000 (0.114)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.29601049423218
Clustering criterion: eps: 0.700
==> Statistics for epoch 0: 859 clusters
Epoch: [0][20/200]	Time 0.381 (0.738)	Data 0.000 (0.052)	Loss 3.068 (4.637)
Epoch: [0][40/200]	Time 0.202 (0.511)	Data 0.001 (0.065)	Loss 5.504 (4.672)
Epoch: [0][60/200]	Time 0.218 (0.437)	Data 0.001 (0.070)	Loss 3.828 (4.743)
Epoch: [0][80/200]	Time 0.205 (0.396)	Data 0.001 (0.070)	Loss 3.327 (4.494)
Epoch: [0][100/200]	Time 0.203 (0.358)	Data 0.000 (0.056)	Loss 3.426 (4.276)
Epoch: [0][120/200]	Time 0.206 (0.346)	Data 0.001 (0.060)	Loss 3.075 (4.085)
Epoch: [0][140/200]	Time 0.205 (0.335)	Data 0.001 (0.061)	Loss 2.384 (3.937)
Epoch: [0][160/200]	Time 0.206 (0.328)	Data 0.001 (0.062)	Loss 2.457 (3.802)
Epoch: [0][180/200]	Time 0.207 (0.316)	Data 0.000 (0.057)	Loss 2.460 (3.674)
Epoch: [0][200/200]	Time 0.204 (0.313)	Data 0.001 (0.059)	Loss 2.823 (3.573)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.202)	Data 0.000 (0.129)	
Extract Features: [100/128]	Time 0.069 (0.186)	Data 0.000 (0.112)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.20764780044556
==> Statistics for epoch 1: 887 clusters
Epoch: [1][20/200]	Time 0.205 (0.261)	Data 0.001 (0.053)	Loss 0.985 (0.767)
Epoch: [1][40/200]	Time 0.205 (0.274)	Data 0.001 (0.067)	Loss 2.048 (1.290)
Epoch: [1][60/200]	Time 0.204 (0.277)	Data 0.000 (0.070)	Loss 2.878 (1.718)
Epoch: [1][80/200]	Time 0.204 (0.260)	Data 0.000 (0.054)	Loss 2.209 (1.936)
Epoch: [1][100/200]	Time 0.202 (0.266)	Data 0.000 (0.060)	Loss 2.847 (2.035)
Epoch: [1][120/200]	Time 0.203 (0.269)	Data 0.000 (0.062)	Loss 2.898 (2.104)
Epoch: [1][140/200]	Time 0.206 (0.270)	Data 0.001 (0.064)	Loss 2.066 (2.143)
Epoch: [1][160/200]	Time 0.263 (0.263)	Data 0.062 (0.057)	Loss 2.682 (2.173)
Epoch: [1][180/200]	Time 0.203 (0.266)	Data 0.000 (0.060)	Loss 2.394 (2.189)
Epoch: [1][200/200]	Time 0.203 (0.267)	Data 0.000 (0.061)	Loss 2.323 (2.200)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.072 (0.203)	Data 0.000 (0.129)	
Extract Features: [100/128]	Time 0.069 (0.191)	Data 0.000 (0.118)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.16909980773926
==> Statistics for epoch 2: 914 clusters
Epoch: [2][20/200]	Time 0.205 (0.260)	Data 0.001 (0.050)	Loss 0.455 (0.553)
Epoch: [2][40/200]	Time 0.208 (0.273)	Data 0.001 (0.066)	Loss 2.258 (1.049)
Epoch: [2][60/200]	Time 0.206 (0.280)	Data 0.001 (0.070)	Loss 2.546 (1.416)
Epoch: [2][80/200]	Time 0.203 (0.262)	Data 0.000 (0.053)	Loss 2.600 (1.630)
Epoch: [2][100/200]	Time 0.207 (0.267)	Data 0.001 (0.059)	Loss 1.762 (1.741)
Epoch: [2][120/200]	Time 0.205 (0.270)	Data 0.000 (0.062)	Loss 1.979 (1.813)
Epoch: [2][140/200]	Time 0.204 (0.261)	Data 0.000 (0.053)	Loss 2.257 (1.858)
Epoch: [2][160/200]	Time 0.207 (0.264)	Data 0.000 (0.056)	Loss 2.121 (1.884)
Epoch: [2][180/200]	Time 0.211 (0.266)	Data 0.001 (0.058)	Loss 1.819 (1.912)
Epoch: [2][200/200]	Time 0.213 (0.268)	Data 0.001 (0.061)	Loss 1.880 (1.931)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.121 (0.206)	Data 0.052 (0.133)	
Extract Features: [100/128]	Time 0.169 (0.190)	Data 0.101 (0.119)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.5136878490448
==> Statistics for epoch 3: 947 clusters
Epoch: [3][20/200]	Time 0.202 (0.266)	Data 0.001 (0.053)	Loss 0.472 (0.558)
Epoch: [3][40/200]	Time 0.202 (0.278)	Data 0.001 (0.069)	Loss 1.808 (0.945)
Epoch: [3][60/200]	Time 0.208 (0.283)	Data 0.001 (0.074)	Loss 2.031 (1.335)
Epoch: [3][80/200]	Time 0.201 (0.266)	Data 0.001 (0.058)	Loss 1.682 (1.525)
Epoch: [3][100/200]	Time 0.206 (0.271)	Data 0.001 (0.062)	Loss 2.583 (1.639)
Epoch: [3][120/200]	Time 0.202 (0.273)	Data 0.001 (0.065)	Loss 1.698 (1.707)
Epoch: [3][140/200]	Time 0.208 (0.265)	Data 0.000 (0.057)	Loss 2.289 (1.759)
Epoch: [3][160/200]	Time 0.203 (0.269)	Data 0.001 (0.061)	Loss 2.029 (1.793)
Epoch: [3][180/200]	Time 0.208 (0.271)	Data 0.001 (0.063)	Loss 2.369 (1.827)
Epoch: [3][200/200]	Time 0.201 (0.266)	Data 0.000 (0.057)	Loss 1.874 (1.839)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.068 (0.208)	Data 0.000 (0.138)	
Extract Features: [100/128]	Time 0.069 (0.189)	Data 0.000 (0.118)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.617385149002075
==> Statistics for epoch 4: 911 clusters
Epoch: [4][20/200]	Time 0.203 (0.259)	Data 0.000 (0.054)	Loss 0.418 (0.516)
Epoch: [4][40/200]	Time 0.203 (0.266)	Data 0.001 (0.061)	Loss 1.727 (0.939)
Epoch: [4][60/200]	Time 0.209 (0.274)	Data 0.001 (0.066)	Loss 2.354 (1.299)
Epoch: [4][80/200]	Time 0.210 (0.256)	Data 0.000 (0.050)	Loss 2.005 (1.479)
Epoch: [4][100/200]	Time 0.206 (0.261)	Data 0.001 (0.055)	Loss 2.126 (1.561)
Epoch: [4][120/200]	Time 0.210 (0.266)	Data 0.001 (0.059)	Loss 2.334 (1.629)
Epoch: [4][140/200]	Time 0.201 (0.258)	Data 0.000 (0.051)	Loss 1.852 (1.686)
Epoch: [4][160/200]	Time 0.203 (0.262)	Data 0.001 (0.056)	Loss 2.150 (1.719)
Epoch: [4][180/200]	Time 0.204 (0.263)	Data 0.001 (0.057)	Loss 2.225 (1.749)
Epoch: [4][200/200]	Time 0.210 (0.265)	Data 0.001 (0.058)	Loss 2.233 (1.762)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.113 (0.207)	Data 0.044 (0.137)	
Extract Features: [100/128]	Time 0.233 (0.193)	Data 0.164 (0.122)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.74538469314575
==> Statistics for epoch 5: 886 clusters
Epoch: [5][20/200]	Time 0.209 (0.270)	Data 0.001 (0.058)	Loss 0.382 (0.500)
Epoch: [5][40/200]	Time 0.205 (0.275)	Data 0.001 (0.067)	Loss 2.120 (0.998)
Epoch: [5][60/200]	Time 0.206 (0.280)	Data 0.001 (0.073)	Loss 2.180 (1.327)
Epoch: [5][80/200]	Time 0.204 (0.263)	Data 0.000 (0.055)	Loss 1.879 (1.454)
Epoch: [5][100/200]	Time 0.218 (0.269)	Data 0.009 (0.061)	Loss 1.991 (1.570)
Epoch: [5][120/200]	Time 0.205 (0.271)	Data 0.001 (0.064)	Loss 2.516 (1.639)
Epoch: [5][140/200]	Time 0.249 (0.273)	Data 0.040 (0.065)	Loss 2.169 (1.684)
Epoch: [5][160/200]	Time 0.201 (0.265)	Data 0.000 (0.057)	Loss 2.529 (1.709)
Epoch: [5][180/200]	Time 0.205 (0.267)	Data 0.001 (0.060)	Loss 1.742 (1.734)
Epoch: [5][200/200]	Time 0.203 (0.269)	Data 0.001 (0.062)	Loss 1.790 (1.746)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.208)	Data 0.000 (0.133)	
Extract Features: [100/128]	Time 0.069 (0.188)	Data 0.000 (0.116)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.64345622062683
==> Statistics for epoch 6: 903 clusters
Epoch: [6][20/200]	Time 0.205 (0.262)	Data 0.001 (0.049)	Loss 0.404 (0.474)
Epoch: [6][40/200]	Time 0.205 (0.276)	Data 0.001 (0.067)	Loss 2.232 (0.956)
Epoch: [6][60/200]	Time 0.204 (0.280)	Data 0.001 (0.071)	Loss 2.344 (1.260)
Epoch: [6][80/200]	Time 0.205 (0.265)	Data 0.000 (0.056)	Loss 1.752 (1.442)
Epoch: [6][100/200]	Time 0.207 (0.271)	Data 0.001 (0.063)	Loss 1.671 (1.545)
Epoch: [6][120/200]	Time 0.209 (0.275)	Data 0.001 (0.067)	Loss 1.971 (1.615)
Epoch: [6][140/200]	Time 0.203 (0.268)	Data 0.000 (0.060)	Loss 1.872 (1.665)
Epoch: [6][160/200]	Time 0.207 (0.271)	Data 0.000 (0.064)	Loss 1.531 (1.690)
Epoch: [6][180/200]	Time 0.205 (0.275)	Data 0.000 (0.067)	Loss 1.821 (1.712)
Epoch: [6][200/200]	Time 0.205 (0.277)	Data 0.001 (0.069)	Loss 1.392 (1.731)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.207)	Data 0.000 (0.135)	
Extract Features: [100/128]	Time 0.068 (0.188)	Data 0.000 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.051955461502075
==> Statistics for epoch 7: 877 clusters
Epoch: [7][20/200]	Time 0.206 (0.257)	Data 0.001 (0.052)	Loss 0.362 (0.443)
Epoch: [7][40/200]	Time 0.206 (0.275)	Data 0.001 (0.070)	Loss 2.140 (0.878)
Epoch: [7][60/200]	Time 0.213 (0.282)	Data 0.001 (0.077)	Loss 1.549 (1.200)
Epoch: [7][80/200]	Time 0.207 (0.264)	Data 0.000 (0.058)	Loss 1.633 (1.383)
Epoch: [7][100/200]	Time 0.208 (0.271)	Data 0.001 (0.063)	Loss 2.175 (1.458)
Epoch: [7][120/200]	Time 0.205 (0.274)	Data 0.001 (0.066)	Loss 2.042 (1.523)
Epoch: [7][140/200]	Time 0.248 (0.277)	Data 0.045 (0.069)	Loss 1.654 (1.578)
Epoch: [7][160/200]	Time 0.212 (0.270)	Data 0.001 (0.061)	Loss 1.960 (1.616)
Epoch: [7][180/200]	Time 0.205 (0.273)	Data 0.001 (0.064)	Loss 1.651 (1.649)
Epoch: [7][200/200]	Time 0.203 (0.274)	Data 0.001 (0.067)	Loss 2.034 (1.674)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.100 (0.205)	Data 0.032 (0.135)	
Extract Features: [100/128]	Time 0.177 (0.191)	Data 0.107 (0.119)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.364168643951416
==> Statistics for epoch 8: 923 clusters
Epoch: [8][20/200]	Time 0.203 (0.258)	Data 0.001 (0.052)	Loss 0.401 (0.478)
Epoch: [8][40/200]	Time 0.206 (0.271)	Data 0.001 (0.062)	Loss 1.903 (0.873)
Epoch: [8][60/200]	Time 0.204 (0.276)	Data 0.001 (0.070)	Loss 1.427 (1.242)
Epoch: [8][80/200]	Time 0.203 (0.260)	Data 0.000 (0.054)	Loss 2.063 (1.397)
Epoch: [8][100/200]	Time 0.209 (0.266)	Data 0.001 (0.060)	Loss 2.123 (1.496)
Epoch: [8][120/200]	Time 0.206 (0.271)	Data 0.001 (0.064)	Loss 1.557 (1.563)
Epoch: [8][140/200]	Time 0.202 (0.262)	Data 0.000 (0.056)	Loss 1.875 (1.625)
Epoch: [8][160/200]	Time 0.206 (0.264)	Data 0.001 (0.059)	Loss 1.899 (1.654)
Epoch: [8][180/200]	Time 0.203 (0.267)	Data 0.001 (0.062)	Loss 1.554 (1.682)
Epoch: [8][200/200]	Time 0.203 (0.269)	Data 0.001 (0.063)	Loss 1.707 (1.709)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.207)	Data 0.000 (0.134)	
Extract Features: [100/128]	Time 0.070 (0.194)	Data 0.000 (0.120)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.77690148353577
==> Statistics for epoch 9: 916 clusters
Epoch: [9][20/200]	Time 0.208 (0.256)	Data 0.001 (0.051)	Loss 0.408 (0.471)
Epoch: [9][40/200]	Time 0.205 (0.272)	Data 0.001 (0.067)	Loss 1.825 (0.883)
Epoch: [9][60/200]	Time 0.205 (0.278)	Data 0.001 (0.073)	Loss 1.662 (1.237)
Epoch: [9][80/200]	Time 0.215 (0.265)	Data 0.000 (0.057)	Loss 2.098 (1.388)
Epoch: [9][100/200]	Time 0.205 (0.268)	Data 0.001 (0.060)	Loss 2.065 (1.464)
Epoch: [9][120/200]	Time 0.207 (0.272)	Data 0.001 (0.065)	Loss 1.686 (1.541)
Epoch: [9][140/200]	Time 0.207 (0.264)	Data 0.000 (0.057)	Loss 1.835 (1.603)
Epoch: [9][160/200]	Time 0.204 (0.266)	Data 0.001 (0.059)	Loss 2.066 (1.641)
Epoch: [9][180/200]	Time 0.206 (0.268)	Data 0.001 (0.061)	Loss 1.798 (1.650)
Epoch: [9][200/200]	Time 0.208 (0.270)	Data 0.001 (0.063)	Loss 1.785 (1.677)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.068 (0.208)	Data 0.000 (0.138)	
Extract Features: [100/128]	Time 0.077 (0.189)	Data 0.000 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.94145846366882
==> Statistics for epoch 10: 929 clusters
Epoch: [10][20/200]	Time 0.203 (0.268)	Data 0.001 (0.055)	Loss 0.363 (0.428)
Epoch: [10][40/200]	Time 0.205 (0.279)	Data 0.001 (0.071)	Loss 2.208 (0.790)
Epoch: [10][60/200]	Time 0.203 (0.283)	Data 0.001 (0.076)	Loss 2.106 (1.157)
Epoch: [10][80/200]	Time 0.202 (0.266)	Data 0.000 (0.060)	Loss 2.185 (1.317)
Epoch: [10][100/200]	Time 0.267 (0.272)	Data 0.053 (0.066)	Loss 2.120 (1.415)
Epoch: [10][120/200]	Time 0.205 (0.275)	Data 0.001 (0.069)	Loss 1.832 (1.496)
Epoch: [10][140/200]	Time 0.206 (0.266)	Data 0.000 (0.060)	Loss 1.972 (1.545)
Epoch: [10][160/200]	Time 0.210 (0.270)	Data 0.001 (0.064)	Loss 1.439 (1.581)
Epoch: [10][180/200]	Time 0.203 (0.273)	Data 0.001 (0.067)	Loss 2.126 (1.614)
Epoch: [10][200/200]	Time 0.206 (0.267)	Data 0.000 (0.061)	Loss 2.225 (1.628)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.265 (0.208)	Data 0.191 (0.135)	
Extract Features: [100/128]	Time 0.071 (0.191)	Data 0.000 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.92193102836609
==> Statistics for epoch 11: 950 clusters
Epoch: [11][20/200]	Time 0.203 (0.261)	Data 0.001 (0.055)	Loss 0.359 (0.439)
Epoch: [11][40/200]	Time 0.207 (0.278)	Data 0.001 (0.072)	Loss 2.011 (0.825)
Epoch: [11][60/200]	Time 0.207 (0.282)	Data 0.001 (0.076)	Loss 1.805 (1.208)
Epoch: [11][80/200]	Time 0.218 (0.267)	Data 0.015 (0.061)	Loss 1.786 (1.372)
Epoch: [11][100/200]	Time 0.202 (0.273)	Data 0.000 (0.067)	Loss 1.807 (1.499)
Epoch: [11][120/200]	Time 0.209 (0.277)	Data 0.000 (0.069)	Loss 2.211 (1.598)
Epoch: [11][140/200]	Time 0.206 (0.269)	Data 0.000 (0.061)	Loss 1.641 (1.644)
Epoch: [11][160/200]	Time 0.203 (0.272)	Data 0.000 (0.065)	Loss 1.748 (1.676)
Epoch: [11][180/200]	Time 0.204 (0.274)	Data 0.001 (0.067)	Loss 1.743 (1.702)
Epoch: [11][200/200]	Time 0.204 (0.269)	Data 0.000 (0.061)	Loss 2.035 (1.724)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.078 (0.207)	Data 0.000 (0.133)	
Extract Features: [100/128]	Time 0.087 (0.187)	Data 0.019 (0.116)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.02039575576782
==> Statistics for epoch 12: 923 clusters
Epoch: [12][20/200]	Time 0.205 (0.257)	Data 0.001 (0.053)	Loss 0.415 (0.444)
Epoch: [12][40/200]	Time 0.373 (0.273)	Data 0.001 (0.065)	Loss 1.238 (0.858)
Epoch: [12][60/200]	Time 0.204 (0.273)	Data 0.001 (0.066)	Loss 1.874 (1.191)
Epoch: [12][80/200]	Time 0.204 (0.257)	Data 0.000 (0.052)	Loss 1.664 (1.327)
Epoch: [12][100/200]	Time 0.203 (0.262)	Data 0.001 (0.057)	Loss 1.754 (1.449)
Epoch: [12][120/200]	Time 0.203 (0.265)	Data 0.001 (0.060)	Loss 1.733 (1.538)
Epoch: [12][140/200]	Time 0.203 (0.258)	Data 0.000 (0.053)	Loss 2.497 (1.585)
Epoch: [12][160/200]	Time 0.217 (0.260)	Data 0.000 (0.056)	Loss 2.658 (1.644)
Epoch: [12][180/200]	Time 0.206 (0.263)	Data 0.001 (0.059)	Loss 1.356 (1.672)
Epoch: [12][200/200]	Time 0.202 (0.265)	Data 0.001 (0.060)	Loss 2.046 (1.696)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.208 (0.205)	Data 0.138 (0.133)	
Extract Features: [100/128]	Time 0.068 (0.188)	Data 0.000 (0.118)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.027503490448
==> Statistics for epoch 13: 933 clusters
Epoch: [13][20/200]	Time 0.205 (0.277)	Data 0.000 (0.063)	Loss 0.466 (0.424)
Epoch: [13][40/200]	Time 0.207 (0.286)	Data 0.000 (0.076)	Loss 2.193 (0.768)
Epoch: [13][60/200]	Time 0.201 (0.283)	Data 0.001 (0.074)	Loss 1.969 (1.116)
Epoch: [13][80/200]	Time 0.202 (0.266)	Data 0.000 (0.058)	Loss 1.210 (1.282)
Epoch: [13][100/200]	Time 0.254 (0.270)	Data 0.053 (0.063)	Loss 2.485 (1.389)
Epoch: [13][120/200]	Time 0.205 (0.272)	Data 0.001 (0.065)	Loss 1.556 (1.452)
Epoch: [13][140/200]	Time 0.208 (0.264)	Data 0.000 (0.057)	Loss 2.133 (1.502)
Epoch: [13][160/200]	Time 0.204 (0.267)	Data 0.001 (0.060)	Loss 1.808 (1.556)
Epoch: [13][180/200]	Time 0.202 (0.269)	Data 0.000 (0.062)	Loss 1.569 (1.586)
Epoch: [13][200/200]	Time 0.248 (0.264)	Data 0.046 (0.057)	Loss 1.820 (1.610)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.104 (0.208)	Data 0.031 (0.134)	
Extract Features: [100/128]	Time 0.067 (0.191)	Data 0.000 (0.118)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.4894905090332
==> Statistics for epoch 14: 920 clusters
Epoch: [14][20/200]	Time 0.205 (0.263)	Data 0.001 (0.057)	Loss 0.276 (0.439)
Epoch: [14][40/200]	Time 0.207 (0.276)	Data 0.001 (0.071)	Loss 1.568 (0.831)
Epoch: [14][60/200]	Time 0.203 (0.280)	Data 0.001 (0.072)	Loss 2.378 (1.190)
Epoch: [14][80/200]	Time 0.201 (0.263)	Data 0.000 (0.057)	Loss 1.656 (1.340)
Epoch: [14][100/200]	Time 0.204 (0.268)	Data 0.001 (0.062)	Loss 1.933 (1.425)
Epoch: [14][120/200]	Time 0.203 (0.270)	Data 0.001 (0.065)	Loss 2.265 (1.491)
Epoch: [14][140/200]	Time 0.204 (0.261)	Data 0.000 (0.056)	Loss 2.037 (1.538)
Epoch: [14][160/200]	Time 0.206 (0.264)	Data 0.000 (0.059)	Loss 2.503 (1.562)
Epoch: [14][180/200]	Time 0.209 (0.266)	Data 0.001 (0.061)	Loss 1.238 (1.601)
Epoch: [14][200/200]	Time 0.204 (0.269)	Data 0.001 (0.064)	Loss 2.357 (1.622)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.214)	Data 0.000 (0.141)	
Extract Features: [100/128]	Time 0.370 (0.194)	Data 0.301 (0.121)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.23137283325195
==> Statistics for epoch 15: 915 clusters
Epoch: [15][20/200]	Time 0.213 (0.261)	Data 0.001 (0.056)	Loss 0.328 (0.373)
Epoch: [15][40/200]	Time 0.209 (0.274)	Data 0.001 (0.068)	Loss 1.886 (0.802)
Epoch: [15][60/200]	Time 0.201 (0.276)	Data 0.001 (0.070)	Loss 1.655 (1.096)
Epoch: [15][80/200]	Time 0.204 (0.264)	Data 0.000 (0.057)	Loss 1.567 (1.272)
Epoch: [15][100/200]	Time 0.202 (0.268)	Data 0.001 (0.062)	Loss 1.425 (1.362)
Epoch: [15][120/200]	Time 0.202 (0.270)	Data 0.001 (0.065)	Loss 1.580 (1.449)
Epoch: [15][140/200]	Time 0.200 (0.261)	Data 0.000 (0.056)	Loss 1.571 (1.488)
Epoch: [15][160/200]	Time 0.211 (0.265)	Data 0.001 (0.059)	Loss 1.703 (1.518)
Epoch: [15][180/200]	Time 0.209 (0.267)	Data 0.000 (0.061)	Loss 2.083 (1.550)
Epoch: [15][200/200]	Time 0.209 (0.267)	Data 0.002 (0.062)	Loss 1.903 (1.568)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.191 (0.211)	Data 0.122 (0.136)	
Extract Features: [100/128]	Time 0.195 (0.191)	Data 0.128 (0.119)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.71812462806702
==> Statistics for epoch 16: 958 clusters
Epoch: [16][20/200]	Time 0.206 (0.262)	Data 0.001 (0.056)	Loss 0.385 (0.419)
Epoch: [16][40/200]	Time 0.205 (0.277)	Data 0.001 (0.070)	Loss 1.665 (0.782)
Epoch: [16][60/200]	Time 0.212 (0.278)	Data 0.001 (0.072)	Loss 1.527 (1.095)
Epoch: [16][80/200]	Time 0.206 (0.260)	Data 0.001 (0.054)	Loss 1.862 (1.255)
Epoch: [16][100/200]	Time 0.208 (0.264)	Data 0.001 (0.058)	Loss 1.954 (1.360)
Epoch: [16][120/200]	Time 0.205 (0.268)	Data 0.001 (0.061)	Loss 1.980 (1.448)
Epoch: [16][140/200]	Time 0.206 (0.260)	Data 0.000 (0.053)	Loss 1.532 (1.503)
Epoch: [16][160/200]	Time 0.204 (0.264)	Data 0.001 (0.057)	Loss 1.818 (1.552)
Epoch: [16][180/200]	Time 0.207 (0.269)	Data 0.001 (0.062)	Loss 1.936 (1.580)
Epoch: [16][200/200]	Time 0.204 (0.264)	Data 0.000 (0.056)	Loss 1.681 (1.603)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.208)	Data 0.000 (0.138)	
Extract Features: [100/128]	Time 0.070 (0.188)	Data 0.000 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.89147710800171
==> Statistics for epoch 17: 949 clusters
Epoch: [17][20/200]	Time 0.202 (0.254)	Data 0.001 (0.048)	Loss 0.781 (0.408)
Epoch: [17][40/200]	Time 0.204 (0.272)	Data 0.001 (0.066)	Loss 1.927 (0.724)
Epoch: [17][60/200]	Time 0.203 (0.275)	Data 0.001 (0.070)	Loss 1.660 (1.080)
Epoch: [17][80/200]	Time 0.205 (0.259)	Data 0.001 (0.053)	Loss 1.622 (1.242)
Epoch: [17][100/200]	Time 0.270 (0.266)	Data 0.065 (0.061)	Loss 1.701 (1.348)
Epoch: [17][120/200]	Time 0.204 (0.270)	Data 0.001 (0.064)	Loss 1.868 (1.422)
Epoch: [17][140/200]	Time 0.214 (0.262)	Data 0.000 (0.056)	Loss 1.892 (1.477)
Epoch: [17][160/200]	Time 0.207 (0.267)	Data 0.001 (0.061)	Loss 1.390 (1.501)
Epoch: [17][180/200]	Time 0.202 (0.270)	Data 0.001 (0.063)	Loss 1.879 (1.538)
Epoch: [17][200/200]	Time 0.209 (0.264)	Data 0.001 (0.057)	Loss 1.991 (1.555)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.070 (0.205)	Data 0.000 (0.134)	
Extract Features: [100/128]	Time 0.069 (0.189)	Data 0.000 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.79588174819946
==> Statistics for epoch 18: 943 clusters
Epoch: [18][20/200]	Time 0.206 (0.269)	Data 0.001 (0.063)	Loss 0.401 (0.366)
Epoch: [18][40/200]	Time 0.203 (0.280)	Data 0.001 (0.075)	Loss 1.727 (0.716)
Epoch: [18][60/200]	Time 0.205 (0.284)	Data 0.001 (0.080)	Loss 1.703 (1.079)
Epoch: [18][80/200]	Time 0.205 (0.268)	Data 0.000 (0.061)	Loss 1.645 (1.245)
Epoch: [18][100/200]	Time 0.207 (0.270)	Data 0.001 (0.064)	Loss 1.889 (1.328)
Epoch: [18][120/200]	Time 0.208 (0.271)	Data 0.001 (0.065)	Loss 1.616 (1.406)
Epoch: [18][140/200]	Time 0.205 (0.263)	Data 0.000 (0.056)	Loss 1.808 (1.455)
Epoch: [18][160/200]	Time 0.201 (0.267)	Data 0.001 (0.060)	Loss 1.894 (1.487)
Epoch: [18][180/200]	Time 0.205 (0.269)	Data 0.001 (0.063)	Loss 1.643 (1.517)
Epoch: [18][200/200]	Time 0.344 (0.264)	Data 0.000 (0.057)	Loss 1.877 (1.538)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.068 (0.214)	Data 0.000 (0.144)	
Extract Features: [100/128]	Time 0.069 (0.191)	Data 0.000 (0.120)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.57480192184448
==> Statistics for epoch 19: 928 clusters
Epoch: [19][20/200]	Time 0.206 (0.268)	Data 0.001 (0.063)	Loss 0.403 (0.379)
Epoch: [19][40/200]	Time 0.201 (0.281)	Data 0.001 (0.076)	Loss 1.980 (0.756)
Epoch: [19][60/200]	Time 0.203 (0.283)	Data 0.001 (0.078)	Loss 1.807 (1.049)
Epoch: [19][80/200]	Time 0.206 (0.266)	Data 0.000 (0.060)	Loss 1.576 (1.225)
Epoch: [19][100/200]	Time 0.220 (0.271)	Data 0.016 (0.065)	Loss 1.473 (1.328)
Epoch: [19][120/200]	Time 0.206 (0.273)	Data 0.001 (0.067)	Loss 1.509 (1.390)
Epoch: [19][140/200]	Time 0.204 (0.266)	Data 0.000 (0.059)	Loss 1.900 (1.450)
Epoch: [19][160/200]	Time 0.204 (0.269)	Data 0.001 (0.062)	Loss 1.594 (1.485)
Epoch: [19][180/200]	Time 0.207 (0.271)	Data 0.001 (0.064)	Loss 1.839 (1.513)
Epoch: [19][200/200]	Time 0.203 (0.264)	Data 0.000 (0.058)	Loss 1.316 (1.524)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.209)	Data 0.000 (0.139)	
Extract Features: [100/128]	Time 0.069 (0.190)	Data 0.000 (0.119)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.51349949836731
==> Statistics for epoch 20: 943 clusters
Epoch: [20][20/200]	Time 0.211 (0.259)	Data 0.001 (0.054)	Loss 0.506 (0.366)
Epoch: [20][40/200]	Time 0.203 (0.268)	Data 0.001 (0.063)	Loss 1.752 (0.687)
Epoch: [20][60/200]	Time 0.203 (0.272)	Data 0.001 (0.067)	Loss 1.645 (1.011)
Epoch: [20][80/200]	Time 0.225 (0.259)	Data 0.015 (0.054)	Loss 1.758 (1.165)
Epoch: [20][100/200]	Time 0.205 (0.264)	Data 0.001 (0.059)	Loss 1.731 (1.261)
Epoch: [20][120/200]	Time 0.204 (0.266)	Data 0.001 (0.061)	Loss 1.727 (1.323)
Epoch: [20][140/200]	Time 0.204 (0.258)	Data 0.000 (0.053)	Loss 2.235 (1.360)
Epoch: [20][160/200]	Time 0.205 (0.262)	Data 0.001 (0.056)	Loss 1.817 (1.391)
Epoch: [20][180/200]	Time 0.204 (0.266)	Data 0.001 (0.059)	Loss 1.727 (1.404)
Epoch: [20][200/200]	Time 0.203 (0.260)	Data 0.000 (0.054)	Loss 1.603 (1.428)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.068 (0.210)	Data 0.001 (0.135)	
Extract Features: [100/128]	Time 0.069 (0.191)	Data 0.000 (0.119)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.843788862228394
==> Statistics for epoch 21: 955 clusters
Epoch: [21][20/200]	Time 0.211 (0.265)	Data 0.001 (0.060)	Loss 0.229 (0.354)
Epoch: [21][40/200]	Time 0.205 (0.279)	Data 0.001 (0.073)	Loss 1.861 (0.699)
Epoch: [21][60/200]	Time 0.203 (0.280)	Data 0.001 (0.074)	Loss 1.577 (1.027)
Epoch: [21][80/200]	Time 0.202 (0.268)	Data 0.001 (0.063)	Loss 2.021 (1.206)
Epoch: [21][100/200]	Time 0.300 (0.275)	Data 0.095 (0.068)	Loss 1.627 (1.284)
Epoch: [21][120/200]	Time 0.205 (0.277)	Data 0.001 (0.071)	Loss 1.357 (1.346)
Epoch: [21][140/200]	Time 0.217 (0.270)	Data 0.007 (0.064)	Loss 1.511 (1.396)
Epoch: [21][160/200]	Time 0.205 (0.272)	Data 0.001 (0.065)	Loss 2.013 (1.436)
Epoch: [21][180/200]	Time 0.214 (0.274)	Data 0.000 (0.067)	Loss 1.532 (1.460)
Epoch: [21][200/200]	Time 0.203 (0.269)	Data 0.000 (0.062)	Loss 1.954 (1.481)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.209)	Data 0.000 (0.140)	
Extract Features: [100/128]	Time 0.070 (0.189)	Data 0.000 (0.118)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.04932141304016
==> Statistics for epoch 22: 941 clusters
Epoch: [22][20/200]	Time 0.203 (0.259)	Data 0.001 (0.054)	Loss 0.303 (0.387)
Epoch: [22][40/200]	Time 0.204 (0.276)	Data 0.001 (0.068)	Loss 1.732 (0.744)
Epoch: [22][60/200]	Time 0.202 (0.278)	Data 0.001 (0.071)	Loss 1.254 (1.021)
Epoch: [22][80/200]	Time 0.205 (0.262)	Data 0.001 (0.056)	Loss 2.098 (1.182)
Epoch: [22][100/200]	Time 0.205 (0.268)	Data 0.001 (0.060)	Loss 1.503 (1.275)
Epoch: [22][120/200]	Time 0.207 (0.271)	Data 0.001 (0.063)	Loss 1.247 (1.331)
Epoch: [22][140/200]	Time 0.212 (0.262)	Data 0.000 (0.055)	Loss 1.785 (1.392)
Epoch: [22][160/200]	Time 0.202 (0.264)	Data 0.000 (0.057)	Loss 1.683 (1.419)
Epoch: [22][180/200]	Time 0.201 (0.266)	Data 0.001 (0.060)	Loss 1.729 (1.443)
Epoch: [22][200/200]	Time 0.202 (0.260)	Data 0.000 (0.054)	Loss 1.875 (1.460)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.068 (0.207)	Data 0.000 (0.135)	
Extract Features: [100/128]	Time 0.069 (0.190)	Data 0.000 (0.118)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.614102840423584
==> Statistics for epoch 23: 947 clusters
Epoch: [23][20/200]	Time 0.210 (0.257)	Data 0.001 (0.049)	Loss 0.266 (0.327)
Epoch: [23][40/200]	Time 0.209 (0.274)	Data 0.001 (0.068)	Loss 2.387 (0.662)
Epoch: [23][60/200]	Time 0.203 (0.277)	Data 0.001 (0.071)	Loss 1.678 (0.994)
Epoch: [23][80/200]	Time 0.204 (0.262)	Data 0.001 (0.056)	Loss 2.021 (1.153)
Epoch: [23][100/200]	Time 0.292 (0.270)	Data 0.082 (0.063)	Loss 1.898 (1.241)
Epoch: [23][120/200]	Time 0.205 (0.273)	Data 0.001 (0.066)	Loss 1.459 (1.303)
Epoch: [23][140/200]	Time 0.205 (0.265)	Data 0.000 (0.058)	Loss 1.562 (1.343)
Epoch: [23][160/200]	Time 0.206 (0.269)	Data 0.001 (0.062)	Loss 1.555 (1.387)
Epoch: [23][180/200]	Time 0.204 (0.270)	Data 0.001 (0.063)	Loss 1.032 (1.412)
Epoch: [23][200/200]	Time 0.206 (0.264)	Data 0.000 (0.057)	Loss 1.458 (1.437)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.207)	Data 0.000 (0.134)	
Extract Features: [100/128]	Time 0.069 (0.187)	Data 0.000 (0.114)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.63977336883545
==> Statistics for epoch 24: 953 clusters
Epoch: [24][20/200]	Time 0.208 (0.254)	Data 0.001 (0.049)	Loss 0.215 (0.346)
Epoch: [24][40/200]	Time 0.203 (0.268)	Data 0.001 (0.063)	Loss 1.641 (0.708)
Epoch: [24][60/200]	Time 0.205 (0.272)	Data 0.001 (0.067)	Loss 1.811 (0.993)
Epoch: [24][80/200]	Time 0.200 (0.258)	Data 0.000 (0.053)	Loss 1.975 (1.168)
Epoch: [24][100/200]	Time 0.204 (0.264)	Data 0.001 (0.059)	Loss 1.643 (1.249)
Epoch: [24][120/200]	Time 0.205 (0.269)	Data 0.001 (0.064)	Loss 1.598 (1.338)
Epoch: [24][140/200]	Time 0.210 (0.261)	Data 0.000 (0.056)	Loss 1.635 (1.381)
Epoch: [24][160/200]	Time 0.206 (0.264)	Data 0.001 (0.059)	Loss 1.757 (1.428)
Epoch: [24][180/200]	Time 0.206 (0.266)	Data 0.001 (0.061)	Loss 2.048 (1.449)
Epoch: [24][200/200]	Time 0.199 (0.261)	Data 0.000 (0.055)	Loss 1.628 (1.464)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.116 (0.204)	Data 0.047 (0.131)	
Extract Features: [100/128]	Time 0.075 (0.191)	Data 0.000 (0.119)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.377361536026
==> Statistics for epoch 25: 957 clusters
Epoch: [25][20/200]	Time 0.205 (0.261)	Data 0.001 (0.054)	Loss 0.276 (0.355)
Epoch: [25][40/200]	Time 0.202 (0.274)	Data 0.001 (0.067)	Loss 1.463 (0.685)
Epoch: [25][60/200]	Time 0.203 (0.283)	Data 0.001 (0.077)	Loss 1.881 (0.979)
Epoch: [25][80/200]	Time 0.203 (0.267)	Data 0.001 (0.059)	Loss 1.616 (1.139)
Epoch: [25][100/200]	Time 0.250 (0.273)	Data 0.047 (0.065)	Loss 2.009 (1.235)
Epoch: [25][120/200]	Time 0.211 (0.277)	Data 0.001 (0.070)	Loss 1.656 (1.301)
Epoch: [25][140/200]	Time 0.206 (0.268)	Data 0.000 (0.062)	Loss 2.012 (1.346)
Epoch: [25][160/200]	Time 0.203 (0.272)	Data 0.001 (0.065)	Loss 1.451 (1.380)
Epoch: [25][180/200]	Time 0.202 (0.274)	Data 0.000 (0.067)	Loss 1.529 (1.416)
Epoch: [25][200/200]	Time 0.210 (0.267)	Data 0.000 (0.060)	Loss 1.689 (1.437)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.070 (0.207)	Data 0.000 (0.137)	
Extract Features: [100/128]	Time 0.069 (0.190)	Data 0.000 (0.119)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.93653893470764
==> Statistics for epoch 26: 971 clusters
Epoch: [26][20/200]	Time 0.212 (0.269)	Data 0.001 (0.054)	Loss 0.189 (0.341)
Epoch: [26][40/200]	Time 0.204 (0.276)	Data 0.001 (0.067)	Loss 1.659 (0.648)
Epoch: [26][60/200]	Time 0.205 (0.254)	Data 0.000 (0.045)	Loss 1.552 (0.956)
Epoch: [26][80/200]	Time 0.214 (0.266)	Data 0.001 (0.055)	Loss 1.905 (1.129)
Epoch: [26][100/200]	Time 0.206 (0.270)	Data 0.000 (0.059)	Loss 1.818 (1.198)
Epoch: [26][120/200]	Time 0.207 (0.261)	Data 0.000 (0.051)	Loss 1.495 (1.281)
Epoch: [26][140/200]	Time 0.202 (0.264)	Data 0.000 (0.054)	Loss 1.664 (1.332)
Epoch: [26][160/200]	Time 0.206 (0.267)	Data 0.001 (0.058)	Loss 1.986 (1.366)
Epoch: [26][180/200]	Time 0.204 (0.262)	Data 0.000 (0.053)	Loss 1.810 (1.404)
Epoch: [26][200/200]	Time 0.217 (0.265)	Data 0.001 (0.057)	Loss 1.713 (1.435)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.170 (0.208)	Data 0.100 (0.134)	
Extract Features: [100/128]	Time 0.067 (0.189)	Data 0.000 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.07261610031128
==> Statistics for epoch 27: 955 clusters
Epoch: [27][20/200]	Time 0.210 (0.268)	Data 0.001 (0.056)	Loss 0.293 (0.324)
Epoch: [27][40/200]	Time 0.205 (0.277)	Data 0.001 (0.068)	Loss 1.254 (0.676)
Epoch: [27][60/200]	Time 0.204 (0.281)	Data 0.001 (0.074)	Loss 1.668 (0.976)
Epoch: [27][80/200]	Time 0.206 (0.264)	Data 0.001 (0.056)	Loss 1.246 (1.125)
Epoch: [27][100/200]	Time 0.203 (0.268)	Data 0.001 (0.060)	Loss 1.849 (1.229)
Epoch: [27][120/200]	Time 0.204 (0.271)	Data 0.001 (0.063)	Loss 1.699 (1.288)
Epoch: [27][140/200]	Time 0.208 (0.263)	Data 0.000 (0.056)	Loss 1.887 (1.346)
Epoch: [27][160/200]	Time 0.205 (0.268)	Data 0.000 (0.060)	Loss 1.138 (1.371)
Epoch: [27][180/200]	Time 0.204 (0.271)	Data 0.000 (0.064)	Loss 1.705 (1.392)
Epoch: [27][200/200]	Time 0.205 (0.265)	Data 0.000 (0.058)	Loss 1.870 (1.413)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.093 (0.208)	Data 0.024 (0.136)	
Extract Features: [100/128]	Time 0.212 (0.190)	Data 0.000 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.60121154785156
==> Statistics for epoch 28: 946 clusters
Epoch: [28][20/200]	Time 0.205 (0.264)	Data 0.001 (0.051)	Loss 0.274 (0.337)
Epoch: [28][40/200]	Time 0.202 (0.270)	Data 0.001 (0.061)	Loss 1.782 (0.684)
Epoch: [28][60/200]	Time 0.200 (0.274)	Data 0.001 (0.067)	Loss 1.392 (0.966)
Epoch: [28][80/200]	Time 0.201 (0.259)	Data 0.000 (0.051)	Loss 2.370 (1.112)
Epoch: [28][100/200]	Time 0.221 (0.263)	Data 0.016 (0.056)	Loss 1.445 (1.206)
Epoch: [28][120/200]	Time 0.210 (0.267)	Data 0.001 (0.060)	Loss 1.961 (1.267)
Epoch: [28][140/200]	Time 0.208 (0.258)	Data 0.000 (0.051)	Loss 1.990 (1.316)
Epoch: [28][160/200]	Time 0.204 (0.262)	Data 0.000 (0.055)	Loss 1.650 (1.339)
Epoch: [28][180/200]	Time 0.206 (0.264)	Data 0.000 (0.058)	Loss 1.635 (1.378)
Epoch: [28][200/200]	Time 0.204 (0.259)	Data 0.000 (0.052)	Loss 1.430 (1.406)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.119 (0.203)	Data 0.050 (0.131)	
Extract Features: [100/128]	Time 0.068 (0.191)	Data 0.000 (0.121)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.57094120979309
==> Statistics for epoch 29: 935 clusters
Epoch: [29][20/200]	Time 0.209 (0.258)	Data 0.001 (0.053)	Loss 0.624 (0.356)
Epoch: [29][40/200]	Time 0.202 (0.274)	Data 0.001 (0.070)	Loss 1.641 (0.665)
Epoch: [29][60/200]	Time 0.204 (0.280)	Data 0.001 (0.075)	Loss 1.429 (0.987)
Epoch: [29][80/200]	Time 0.313 (0.264)	Data 0.109 (0.059)	Loss 1.675 (1.152)
Epoch: [29][100/200]	Time 0.233 (0.271)	Data 0.023 (0.065)	Loss 1.295 (1.225)
Epoch: [29][120/200]	Time 0.212 (0.276)	Data 0.001 (0.070)	Loss 1.381 (1.282)
Epoch: [29][140/200]	Time 0.212 (0.266)	Data 0.001 (0.060)	Loss 1.165 (1.316)
Epoch: [29][160/200]	Time 0.211 (0.269)	Data 0.001 (0.062)	Loss 1.377 (1.352)
Epoch: [29][180/200]	Time 0.202 (0.272)	Data 0.001 (0.065)	Loss 1.198 (1.381)
Epoch: [29][200/200]	Time 0.202 (0.266)	Data 0.000 (0.059)	Loss 1.255 (1.398)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.208)	Data 0.000 (0.139)	
Extract Features: [100/128]	Time 0.069 (0.189)	Data 0.000 (0.118)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.14705300331116
==> Statistics for epoch 30: 937 clusters
Epoch: [30][20/200]	Time 0.203 (0.258)	Data 0.001 (0.053)	Loss 0.461 (0.357)
Epoch: [30][40/200]	Time 0.203 (0.277)	Data 0.001 (0.071)	Loss 2.033 (0.690)
Epoch: [30][60/200]	Time 0.200 (0.280)	Data 0.001 (0.072)	Loss 1.533 (0.986)
Epoch: [30][80/200]	Time 0.200 (0.261)	Data 0.000 (0.055)	Loss 1.486 (1.159)
Epoch: [30][100/200]	Time 0.207 (0.265)	Data 0.001 (0.058)	Loss 1.576 (1.246)
Epoch: [30][120/200]	Time 0.203 (0.269)	Data 0.001 (0.063)	Loss 1.246 (1.313)
Epoch: [30][140/200]	Time 0.203 (0.262)	Data 0.000 (0.054)	Loss 1.404 (1.352)
Epoch: [30][160/200]	Time 0.210 (0.264)	Data 0.001 (0.057)	Loss 1.657 (1.380)
Epoch: [30][180/200]	Time 0.204 (0.267)	Data 0.001 (0.060)	Loss 1.482 (1.405)
Epoch: [30][200/200]	Time 0.204 (0.261)	Data 0.000 (0.054)	Loss 1.253 (1.430)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.068 (0.208)	Data 0.000 (0.136)	
Extract Features: [100/128]	Time 0.068 (0.190)	Data 0.000 (0.118)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.950769901275635
==> Statistics for epoch 31: 950 clusters
Epoch: [31][20/200]	Time 0.213 (0.266)	Data 0.001 (0.060)	Loss 0.180 (0.307)
Epoch: [31][40/200]	Time 0.203 (0.285)	Data 0.001 (0.080)	Loss 1.631 (0.669)
Epoch: [31][60/200]	Time 0.206 (0.292)	Data 0.001 (0.084)	Loss 1.670 (0.938)
Epoch: [31][80/200]	Time 0.206 (0.273)	Data 0.001 (0.066)	Loss 1.429 (1.110)
Epoch: [31][100/200]	Time 0.252 (0.277)	Data 0.048 (0.070)	Loss 1.597 (1.212)
Epoch: [31][120/200]	Time 0.207 (0.280)	Data 0.001 (0.073)	Loss 1.739 (1.270)
Epoch: [31][140/200]	Time 0.204 (0.272)	Data 0.000 (0.065)	Loss 1.570 (1.304)
Epoch: [31][160/200]	Time 0.207 (0.275)	Data 0.001 (0.068)	Loss 1.624 (1.337)
Epoch: [31][180/200]	Time 0.223 (0.277)	Data 0.001 (0.071)	Loss 0.947 (1.366)
Epoch: [31][200/200]	Time 0.207 (0.271)	Data 0.000 (0.064)	Loss 1.412 (1.380)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.206)	Data 0.000 (0.132)	
Extract Features: [100/128]	Time 0.322 (0.189)	Data 0.253 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.85364079475403
==> Statistics for epoch 32: 950 clusters
Epoch: [32][20/200]	Time 0.202 (0.259)	Data 0.000 (0.046)	Loss 0.327 (0.315)
Epoch: [32][40/200]	Time 0.201 (0.267)	Data 0.001 (0.059)	Loss 1.790 (0.648)
Epoch: [32][60/200]	Time 0.203 (0.281)	Data 0.001 (0.074)	Loss 1.450 (1.000)
Epoch: [32][80/200]	Time 0.207 (0.266)	Data 0.000 (0.059)	Loss 1.297 (1.141)
Epoch: [32][100/200]	Time 0.206 (0.272)	Data 0.001 (0.064)	Loss 1.880 (1.259)
Epoch: [32][120/200]	Time 0.205 (0.277)	Data 0.001 (0.069)	Loss 1.431 (1.305)
Epoch: [32][140/200]	Time 0.202 (0.267)	Data 0.000 (0.060)	Loss 1.761 (1.361)
Epoch: [32][160/200]	Time 0.205 (0.270)	Data 0.001 (0.062)	Loss 1.574 (1.395)
Epoch: [32][180/200]	Time 0.205 (0.272)	Data 0.001 (0.064)	Loss 1.705 (1.421)
Epoch: [32][200/200]	Time 0.205 (0.266)	Data 0.000 (0.058)	Loss 2.185 (1.438)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.071 (0.210)	Data 0.000 (0.140)	
Extract Features: [100/128]	Time 0.069 (0.189)	Data 0.000 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.080442667007446
==> Statistics for epoch 33: 942 clusters
Epoch: [33][20/200]	Time 0.207 (0.264)	Data 0.001 (0.058)	Loss 0.311 (0.316)
Epoch: [33][40/200]	Time 0.204 (0.280)	Data 0.000 (0.072)	Loss 1.803 (0.652)
Epoch: [33][60/200]	Time 0.204 (0.283)	Data 0.001 (0.074)	Loss 1.774 (0.960)
Epoch: [33][80/200]	Time 0.206 (0.264)	Data 0.001 (0.056)	Loss 1.680 (1.101)
Epoch: [33][100/200]	Time 0.206 (0.269)	Data 0.001 (0.062)	Loss 1.083 (1.189)
Epoch: [33][120/200]	Time 0.208 (0.273)	Data 0.001 (0.066)	Loss 1.403 (1.253)
Epoch: [33][140/200]	Time 0.207 (0.264)	Data 0.000 (0.057)	Loss 1.437 (1.306)
Epoch: [33][160/200]	Time 0.205 (0.266)	Data 0.001 (0.059)	Loss 1.906 (1.352)
Epoch: [33][180/200]	Time 0.203 (0.268)	Data 0.001 (0.061)	Loss 1.531 (1.380)
Epoch: [33][200/200]	Time 0.245 (0.262)	Data 0.043 (0.055)	Loss 1.592 (1.408)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.074 (0.207)	Data 0.000 (0.135)	
Extract Features: [100/128]	Time 0.070 (0.188)	Data 0.000 (0.116)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.912161350250244
==> Statistics for epoch 34: 941 clusters
Epoch: [34][20/200]	Time 0.206 (0.257)	Data 0.001 (0.050)	Loss 0.305 (0.350)
Epoch: [34][40/200]	Time 0.204 (0.274)	Data 0.001 (0.067)	Loss 1.526 (0.716)
Epoch: [34][60/200]	Time 0.203 (0.279)	Data 0.001 (0.073)	Loss 1.377 (1.026)
Epoch: [34][80/200]	Time 0.202 (0.264)	Data 0.001 (0.058)	Loss 1.597 (1.170)
Epoch: [34][100/200]	Time 0.205 (0.268)	Data 0.001 (0.063)	Loss 1.400 (1.248)
Epoch: [34][120/200]	Time 0.205 (0.270)	Data 0.001 (0.064)	Loss 1.414 (1.319)
Epoch: [34][140/200]	Time 0.208 (0.262)	Data 0.000 (0.056)	Loss 1.542 (1.359)
Epoch: [34][160/200]	Time 0.203 (0.265)	Data 0.001 (0.059)	Loss 1.544 (1.388)
Epoch: [34][180/200]	Time 0.206 (0.269)	Data 0.001 (0.062)	Loss 1.997 (1.408)
Epoch: [34][200/200]	Time 0.206 (0.264)	Data 0.000 (0.057)	Loss 1.450 (1.423)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.069 (0.213)	Data 0.000 (0.143)	
Extract Features: [100/128]	Time 0.069 (0.191)	Data 0.000 (0.120)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.709550619125366
==> Statistics for epoch 35: 939 clusters
Epoch: [35][20/200]	Time 0.207 (0.270)	Data 0.000 (0.053)	Loss 0.375 (0.352)
Epoch: [35][40/200]	Time 0.207 (0.278)	Data 0.000 (0.066)	Loss 1.500 (0.670)
Epoch: [35][60/200]	Time 0.222 (0.281)	Data 0.016 (0.071)	Loss 1.303 (0.976)
Epoch: [35][80/200]	Time 0.258 (0.264)	Data 0.053 (0.055)	Loss 1.350 (1.128)
Epoch: [35][100/200]	Time 0.202 (0.269)	Data 0.001 (0.060)	Loss 1.751 (1.210)
Epoch: [35][120/200]	Time 0.207 (0.271)	Data 0.000 (0.063)	Loss 1.779 (1.283)
Epoch: [35][140/200]	Time 0.209 (0.263)	Data 0.000 (0.055)	Loss 1.544 (1.329)
Epoch: [35][160/200]	Time 0.207 (0.266)	Data 0.001 (0.058)	Loss 1.464 (1.367)
Epoch: [35][180/200]	Time 0.205 (0.269)	Data 0.001 (0.062)	Loss 1.891 (1.394)
Epoch: [35][200/200]	Time 0.202 (0.263)	Data 0.000 (0.056)	Loss 2.249 (1.415)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.602 (0.213)	Data 0.531 (0.141)	
Extract Features: [100/128]	Time 0.068 (0.194)	Data 0.000 (0.122)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.636396408081055
==> Statistics for epoch 36: 939 clusters
Epoch: [36][20/200]	Time 0.206 (0.260)	Data 0.001 (0.054)	Loss 0.219 (0.330)
Epoch: [36][40/200]	Time 0.203 (0.272)	Data 0.001 (0.067)	Loss 1.775 (0.664)
Epoch: [36][60/200]	Time 0.202 (0.275)	Data 0.001 (0.071)	Loss 1.189 (0.960)
Epoch: [36][80/200]	Time 0.204 (0.261)	Data 0.001 (0.056)	Loss 1.412 (1.100)
Epoch: [36][100/200]	Time 0.205 (0.266)	Data 0.001 (0.061)	Loss 1.346 (1.198)
Epoch: [36][120/200]	Time 0.205 (0.268)	Data 0.001 (0.063)	Loss 1.704 (1.265)
Epoch: [36][140/200]	Time 0.208 (0.261)	Data 0.000 (0.055)	Loss 1.140 (1.304)
Epoch: [36][160/200]	Time 0.205 (0.264)	Data 0.000 (0.058)	Loss 1.690 (1.350)
Epoch: [36][180/200]	Time 0.206 (0.267)	Data 0.000 (0.060)	Loss 1.663 (1.369)
Epoch: [36][200/200]	Time 0.203 (0.261)	Data 0.000 (0.054)	Loss 1.602 (1.400)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.095 (0.203)	Data 0.026 (0.133)	
Extract Features: [100/128]	Time 0.069 (0.187)	Data 0.000 (0.116)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.297361612319946
==> Statistics for epoch 37: 952 clusters
Epoch: [37][20/200]	Time 0.204 (0.258)	Data 0.001 (0.052)	Loss 0.302 (0.314)
Epoch: [37][40/200]	Time 0.204 (0.277)	Data 0.001 (0.068)	Loss 1.793 (0.642)
Epoch: [37][60/200]	Time 0.203 (0.279)	Data 0.001 (0.071)	Loss 0.859 (0.927)
Epoch: [37][80/200]	Time 0.203 (0.265)	Data 0.001 (0.058)	Loss 1.049 (1.082)
Epoch: [37][100/200]	Time 0.207 (0.269)	Data 0.001 (0.063)	Loss 1.225 (1.185)
Epoch: [37][120/200]	Time 0.203 (0.273)	Data 0.001 (0.065)	Loss 1.992 (1.260)
Epoch: [37][140/200]	Time 0.204 (0.264)	Data 0.000 (0.057)	Loss 1.629 (1.298)
Epoch: [37][160/200]	Time 0.204 (0.269)	Data 0.001 (0.062)	Loss 1.392 (1.324)
Epoch: [37][180/200]	Time 0.203 (0.272)	Data 0.001 (0.065)	Loss 2.377 (1.362)
Epoch: [37][200/200]	Time 0.204 (0.266)	Data 0.000 (0.059)	Loss 1.761 (1.387)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.089 (0.206)	Data 0.018 (0.136)	
Extract Features: [100/128]	Time 0.070 (0.188)	Data 0.000 (0.116)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.2063844203949
==> Statistics for epoch 38: 932 clusters
Epoch: [38][20/200]	Time 0.203 (0.266)	Data 0.001 (0.061)	Loss 0.366 (0.315)
Epoch: [38][40/200]	Time 0.200 (0.277)	Data 0.001 (0.072)	Loss 1.335 (0.625)
Epoch: [38][60/200]	Time 0.205 (0.280)	Data 0.001 (0.075)	Loss 1.212 (0.919)
Epoch: [38][80/200]	Time 0.205 (0.262)	Data 0.000 (0.057)	Loss 2.096 (1.038)
Epoch: [38][100/200]	Time 0.206 (0.269)	Data 0.001 (0.063)	Loss 1.767 (1.160)
Epoch: [38][120/200]	Time 0.205 (0.274)	Data 0.002 (0.067)	Loss 1.712 (1.194)
Epoch: [38][140/200]	Time 0.204 (0.266)	Data 0.000 (0.060)	Loss 1.382 (1.243)
Epoch: [38][160/200]	Time 0.206 (0.269)	Data 0.001 (0.062)	Loss 1.371 (1.270)
Epoch: [38][180/200]	Time 0.203 (0.270)	Data 0.001 (0.064)	Loss 1.988 (1.297)
Epoch: [38][200/200]	Time 0.223 (0.264)	Data 0.017 (0.057)	Loss 1.794 (1.316)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.068 (0.207)	Data 0.000 (0.135)	
Extract Features: [100/128]	Time 0.068 (0.189)	Data 0.000 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.06819486618042
==> Statistics for epoch 39: 942 clusters
Epoch: [39][20/200]	Time 0.203 (0.265)	Data 0.001 (0.060)	Loss 0.197 (0.323)
Epoch: [39][40/200]	Time 0.205 (0.278)	Data 0.001 (0.072)	Loss 1.752 (0.651)
Epoch: [39][60/200]	Time 0.204 (0.282)	Data 0.001 (0.077)	Loss 1.531 (0.941)
Epoch: [39][80/200]	Time 0.207 (0.263)	Data 0.001 (0.058)	Loss 1.562 (1.092)
Epoch: [39][100/200]	Time 0.203 (0.270)	Data 0.001 (0.063)	Loss 1.719 (1.207)
Epoch: [39][120/200]	Time 0.206 (0.273)	Data 0.001 (0.066)	Loss 1.718 (1.266)
Epoch: [39][140/200]	Time 0.205 (0.265)	Data 0.000 (0.059)	Loss 2.437 (1.302)
Epoch: [39][160/200]	Time 0.207 (0.270)	Data 0.001 (0.063)	Loss 1.584 (1.334)
Epoch: [39][180/200]	Time 0.205 (0.272)	Data 0.001 (0.065)	Loss 1.323 (1.354)
Epoch: [39][200/200]	Time 0.205 (0.267)	Data 0.000 (0.060)	Loss 1.161 (1.376)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.122 (0.208)	Data 0.052 (0.135)	
Extract Features: [100/128]	Time 0.069 (0.191)	Data 0.000 (0.120)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.40697193145752
==> Statistics for epoch 40: 958 clusters
Epoch: [40][20/200]	Time 0.203 (0.259)	Data 0.001 (0.055)	Loss 0.303 (0.346)
Epoch: [40][40/200]	Time 0.203 (0.273)	Data 0.001 (0.069)	Loss 1.743 (0.641)
Epoch: [40][60/200]	Time 0.205 (0.279)	Data 0.001 (0.073)	Loss 1.328 (0.954)
Epoch: [40][80/200]	Time 0.206 (0.267)	Data 0.001 (0.061)	Loss 1.858 (1.114)
Epoch: [40][100/200]	Time 0.205 (0.270)	Data 0.001 (0.064)	Loss 2.067 (1.193)
Epoch: [40][120/200]	Time 0.204 (0.272)	Data 0.000 (0.066)	Loss 1.826 (1.260)
Epoch: [40][140/200]	Time 0.201 (0.264)	Data 0.000 (0.059)	Loss 1.261 (1.320)
Epoch: [40][160/200]	Time 0.204 (0.268)	Data 0.000 (0.062)	Loss 1.164 (1.346)
Epoch: [40][180/200]	Time 0.202 (0.271)	Data 0.001 (0.065)	Loss 0.997 (1.379)
Epoch: [40][200/200]	Time 0.201 (0.266)	Data 0.000 (0.060)	Loss 1.290 (1.398)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.068 (0.209)	Data 0.000 (0.137)	
Extract Features: [100/128]	Time 0.068 (0.188)	Data 0.000 (0.118)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.10179376602173
==> Statistics for epoch 41: 963 clusters
Epoch: [41][20/200]	Time 0.203 (0.262)	Data 0.001 (0.057)	Loss 0.566 (0.321)
Epoch: [41][40/200]	Time 0.204 (0.282)	Data 0.001 (0.073)	Loss 1.592 (0.590)
Epoch: [41][60/200]	Time 0.203 (0.257)	Data 0.000 (0.049)	Loss 1.314 (0.903)
Epoch: [41][80/200]	Time 0.205 (0.264)	Data 0.001 (0.056)	Loss 1.804 (1.048)
Epoch: [41][100/200]	Time 0.203 (0.269)	Data 0.000 (0.062)	Loss 1.709 (1.153)
Epoch: [41][120/200]	Time 0.203 (0.260)	Data 0.000 (0.053)	Loss 1.389 (1.232)
Epoch: [41][140/200]	Time 0.208 (0.266)	Data 0.001 (0.059)	Loss 1.802 (1.291)
Epoch: [41][160/200]	Time 0.205 (0.269)	Data 0.001 (0.063)	Loss 1.422 (1.316)
Epoch: [41][180/200]	Time 0.204 (0.263)	Data 0.000 (0.056)	Loss 1.801 (1.350)
Epoch: [41][200/200]	Time 0.207 (0.266)	Data 0.001 (0.060)	Loss 1.346 (1.371)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.070 (0.209)	Data 0.000 (0.136)	
Extract Features: [100/128]	Time 0.069 (0.191)	Data 0.000 (0.118)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.696200132369995
==> Statistics for epoch 42: 947 clusters
Epoch: [42][20/200]	Time 0.211 (0.268)	Data 0.001 (0.062)	Loss 0.177 (0.314)
Epoch: [42][40/200]	Time 0.208 (0.275)	Data 0.001 (0.069)	Loss 1.590 (0.658)
Epoch: [42][60/200]	Time 0.204 (0.276)	Data 0.001 (0.070)	Loss 1.331 (0.946)
Epoch: [42][80/200]	Time 0.204 (0.262)	Data 0.001 (0.056)	Loss 1.483 (1.096)
Epoch: [42][100/200]	Time 0.248 (0.269)	Data 0.046 (0.063)	Loss 1.649 (1.179)
Epoch: [42][120/200]	Time 0.199 (0.272)	Data 0.000 (0.065)	Loss 1.516 (1.255)
Epoch: [42][140/200]	Time 0.209 (0.265)	Data 0.000 (0.058)	Loss 1.369 (1.294)
Epoch: [42][160/200]	Time 0.204 (0.267)	Data 0.001 (0.061)	Loss 1.816 (1.323)
Epoch: [42][180/200]	Time 0.205 (0.269)	Data 0.001 (0.062)	Loss 1.472 (1.346)
Epoch: [42][200/200]	Time 0.205 (0.264)	Data 0.000 (0.056)	Loss 1.559 (1.361)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.363 (0.208)	Data 0.293 (0.139)	
Extract Features: [100/128]	Time 0.069 (0.190)	Data 0.000 (0.119)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.04458975791931
==> Statistics for epoch 43: 947 clusters
Epoch: [43][20/200]	Time 0.214 (0.268)	Data 0.001 (0.062)	Loss 0.233 (0.336)
Epoch: [43][40/200]	Time 0.202 (0.280)	Data 0.001 (0.075)	Loss 1.191 (0.642)
Epoch: [43][60/200]	Time 0.205 (0.284)	Data 0.001 (0.076)	Loss 1.636 (0.925)
Epoch: [43][80/200]	Time 0.204 (0.266)	Data 0.001 (0.058)	Loss 1.411 (1.080)
Epoch: [43][100/200]	Time 0.208 (0.270)	Data 0.001 (0.062)	Loss 1.693 (1.172)
Epoch: [43][120/200]	Time 0.203 (0.272)	Data 0.001 (0.064)	Loss 1.630 (1.248)
Epoch: [43][140/200]	Time 0.211 (0.264)	Data 0.000 (0.056)	Loss 2.229 (1.298)
Epoch: [43][160/200]	Time 0.206 (0.268)	Data 0.001 (0.060)	Loss 1.622 (1.310)
Epoch: [43][180/200]	Time 0.204 (0.270)	Data 0.001 (0.062)	Loss 1.511 (1.352)
Epoch: [43][200/200]	Time 0.203 (0.264)	Data 0.000 (0.057)	Loss 1.396 (1.378)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.077 (0.210)	Data 0.001 (0.137)	
Extract Features: [100/128]	Time 0.070 (0.190)	Data 0.000 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.335402488708496
==> Statistics for epoch 44: 947 clusters
Epoch: [44][20/200]	Time 0.203 (0.254)	Data 0.001 (0.049)	Loss 0.315 (0.348)
Epoch: [44][40/200]	Time 0.202 (0.272)	Data 0.001 (0.068)	Loss 1.488 (0.654)
Epoch: [44][60/200]	Time 0.205 (0.281)	Data 0.001 (0.077)	Loss 1.260 (0.931)
Epoch: [44][80/200]	Time 0.201 (0.262)	Data 0.001 (0.058)	Loss 1.030 (1.070)
Epoch: [44][100/200]	Time 0.288 (0.268)	Data 0.081 (0.063)	Loss 1.314 (1.154)
Epoch: [44][120/200]	Time 0.206 (0.273)	Data 0.001 (0.069)	Loss 1.413 (1.228)
Epoch: [44][140/200]	Time 0.207 (0.266)	Data 0.000 (0.060)	Loss 1.149 (1.272)
Epoch: [44][160/200]	Time 0.207 (0.269)	Data 0.001 (0.063)	Loss 1.882 (1.313)
Epoch: [44][180/200]	Time 0.208 (0.271)	Data 0.001 (0.066)	Loss 1.919 (1.331)
Epoch: [44][200/200]	Time 0.203 (0.265)	Data 0.000 (0.059)	Loss 2.129 (1.361)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.068 (0.209)	Data 0.000 (0.136)	
Extract Features: [100/128]	Time 0.069 (0.190)	Data 0.000 (0.119)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.40834903717041
==> Statistics for epoch 45: 964 clusters
Epoch: [45][20/200]	Time 0.202 (0.267)	Data 0.001 (0.054)	Loss 0.508 (0.351)
Epoch: [45][40/200]	Time 0.203 (0.276)	Data 0.001 (0.068)	Loss 1.811 (0.655)
Epoch: [45][60/200]	Time 0.202 (0.254)	Data 0.000 (0.047)	Loss 1.683 (0.963)
Epoch: [45][80/200]	Time 0.208 (0.261)	Data 0.001 (0.055)	Loss 1.739 (1.125)
Epoch: [45][100/200]	Time 0.205 (0.266)	Data 0.001 (0.060)	Loss 1.478 (1.209)
Epoch: [45][120/200]	Time 0.201 (0.257)	Data 0.000 (0.051)	Loss 1.479 (1.269)
Epoch: [45][140/200]	Time 0.207 (0.261)	Data 0.001 (0.055)	Loss 1.722 (1.311)
Epoch: [45][160/200]	Time 0.209 (0.265)	Data 0.001 (0.059)	Loss 1.307 (1.349)
Epoch: [45][180/200]	Time 0.246 (0.259)	Data 0.046 (0.053)	Loss 1.549 (1.380)
Epoch: [45][200/200]	Time 0.218 (0.261)	Data 0.001 (0.055)	Loss 2.053 (1.410)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.407 (0.209)	Data 0.338 (0.136)	
Extract Features: [100/128]	Time 0.075 (0.191)	Data 0.000 (0.118)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.472086668014526
==> Statistics for epoch 46: 946 clusters
Epoch: [46][20/200]	Time 0.207 (0.270)	Data 0.001 (0.065)	Loss 0.176 (0.325)
Epoch: [46][40/200]	Time 0.215 (0.279)	Data 0.000 (0.074)	Loss 1.639 (0.675)
Epoch: [46][60/200]	Time 0.203 (0.282)	Data 0.000 (0.077)	Loss 1.506 (0.944)
Epoch: [46][80/200]	Time 0.201 (0.263)	Data 0.000 (0.058)	Loss 1.813 (1.090)
Epoch: [46][100/200]	Time 0.207 (0.268)	Data 0.001 (0.063)	Loss 2.091 (1.161)
Epoch: [46][120/200]	Time 0.214 (0.272)	Data 0.001 (0.067)	Loss 1.413 (1.244)
Epoch: [46][140/200]	Time 0.210 (0.264)	Data 0.000 (0.059)	Loss 1.495 (1.289)
Epoch: [46][160/200]	Time 0.207 (0.268)	Data 0.001 (0.063)	Loss 2.272 (1.321)
Epoch: [46][180/200]	Time 0.203 (0.271)	Data 0.001 (0.066)	Loss 1.893 (1.347)
Epoch: [46][200/200]	Time 0.205 (0.266)	Data 0.000 (0.060)	Loss 1.390 (1.368)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.086 (0.206)	Data 0.017 (0.135)	
Extract Features: [100/128]	Time 0.070 (0.188)	Data 0.000 (0.117)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.24874925613403
==> Statistics for epoch 47: 942 clusters
Epoch: [47][20/200]	Time 0.211 (0.264)	Data 0.001 (0.057)	Loss 0.221 (0.309)
Epoch: [47][40/200]	Time 0.202 (0.273)	Data 0.001 (0.068)	Loss 1.588 (0.663)
Epoch: [47][60/200]	Time 0.204 (0.278)	Data 0.001 (0.073)	Loss 1.417 (0.949)
Epoch: [47][80/200]	Time 0.206 (0.262)	Data 0.000 (0.057)	Loss 2.159 (1.103)
Epoch: [47][100/200]	Time 0.206 (0.270)	Data 0.001 (0.063)	Loss 1.651 (1.168)
Epoch: [47][120/200]	Time 0.205 (0.272)	Data 0.001 (0.065)	Loss 1.396 (1.232)
Epoch: [47][140/200]	Time 0.202 (0.264)	Data 0.000 (0.058)	Loss 1.258 (1.266)
Epoch: [47][160/200]	Time 0.209 (0.267)	Data 0.001 (0.060)	Loss 1.547 (1.303)
Epoch: [47][180/200]	Time 0.203 (0.270)	Data 0.001 (0.062)	Loss 1.520 (1.336)
Epoch: [47][200/200]	Time 0.203 (0.264)	Data 0.000 (0.057)	Loss 1.511 (1.352)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.229 (0.204)	Data 0.160 (0.131)	
Extract Features: [100/128]	Time 0.068 (0.187)	Data 0.000 (0.116)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.93871879577637
==> Statistics for epoch 48: 940 clusters
Epoch: [48][20/200]	Time 0.206 (0.260)	Data 0.001 (0.056)	Loss 0.410 (0.326)
Epoch: [48][40/200]	Time 0.201 (0.276)	Data 0.000 (0.069)	Loss 1.514 (0.625)
Epoch: [48][60/200]	Time 0.202 (0.278)	Data 0.001 (0.072)	Loss 1.600 (0.902)
Epoch: [48][80/200]	Time 0.205 (0.263)	Data 0.001 (0.057)	Loss 1.345 (1.066)
Epoch: [48][100/200]	Time 0.210 (0.267)	Data 0.001 (0.061)	Loss 1.285 (1.152)
Epoch: [48][120/200]	Time 0.210 (0.271)	Data 0.001 (0.064)	Loss 2.124 (1.215)
Epoch: [48][140/200]	Time 0.202 (0.263)	Data 0.000 (0.057)	Loss 1.989 (1.268)
Epoch: [48][160/200]	Time 0.204 (0.265)	Data 0.001 (0.059)	Loss 1.945 (1.303)
Epoch: [48][180/200]	Time 0.205 (0.268)	Data 0.001 (0.061)	Loss 1.810 (1.319)
Epoch: [48][200/200]	Time 0.203 (0.262)	Data 0.000 (0.055)	Loss 1.589 (1.345)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.068 (0.207)	Data 0.000 (0.137)	
Extract Features: [100/128]	Time 0.070 (0.188)	Data 0.000 (0.115)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.38420104980469
==> Statistics for epoch 49: 954 clusters
Epoch: [49][20/200]	Time 0.205 (0.252)	Data 0.001 (0.045)	Loss 0.301 (0.350)
Epoch: [49][40/200]	Time 0.204 (0.269)	Data 0.001 (0.064)	Loss 1.811 (0.629)
Epoch: [49][60/200]	Time 0.205 (0.276)	Data 0.001 (0.069)	Loss 1.403 (0.934)
Epoch: [49][80/200]	Time 0.203 (0.260)	Data 0.001 (0.053)	Loss 1.508 (1.088)
Epoch: [49][100/200]	Time 0.204 (0.265)	Data 0.001 (0.059)	Loss 1.111 (1.161)
Epoch: [49][120/200]	Time 0.203 (0.270)	Data 0.001 (0.062)	Loss 1.787 (1.241)
Epoch: [49][140/200]	Time 0.206 (0.263)	Data 0.000 (0.055)	Loss 2.162 (1.284)
Epoch: [49][160/200]	Time 0.205 (0.266)	Data 0.001 (0.058)	Loss 1.755 (1.308)
Epoch: [49][180/200]	Time 0.252 (0.268)	Data 0.049 (0.061)	Loss 1.291 (1.329)
Epoch: [49][200/200]	Time 0.203 (0.262)	Data 0.000 (0.055)	Loss 1.527 (1.354)
Extract Features: [50/367]	Time 0.311 (0.209)	Data 0.087 (0.136)	
Extract Features: [100/367]	Time 0.068 (0.192)	Data 0.000 (0.121)	
Extract Features: [150/367]	Time 0.393 (0.189)	Data 0.323 (0.118)	
Extract Features: [200/367]	Time 0.070 (0.186)	Data 0.000 (0.115)	
Extract Features: [250/367]	Time 0.459 (0.185)	Data 0.384 (0.110)	
Extract Features: [300/367]	Time 0.069 (0.183)	Data 0.000 (0.108)	
Extract Features: [350/367]	Time 0.624 (0.185)	Data 0.557 (0.110)	
Mean AP: 43.1%

 * Finished epoch  49  model mAP: 43.1%  best: 43.1% *

==> Test with the best model:
=> Loaded checkpoint 'log/msmt17/vit_tiny_cion/model_best.pth.tar'
Extract Features: [50/367]	Time 0.068 (0.210)	Data 0.000 (0.137)	
Extract Features: [100/367]	Time 0.111 (0.193)	Data 0.044 (0.122)	
Extract Features: [150/367]	Time 0.281 (0.191)	Data 0.213 (0.121)	
Extract Features: [200/367]	Time 0.274 (0.188)	Data 0.208 (0.118)	
Extract Features: [250/367]	Time 0.260 (0.186)	Data 0.191 (0.116)	
Extract Features: [300/367]	Time 0.345 (0.186)	Data 0.278 (0.115)	
Extract Features: [350/367]	Time 0.181 (0.185)	Data 0.112 (0.115)	
Mean AP: 43.1%
CMC Scores:
  top-1          69.6%
  top-5          80.2%
  top-10         83.8%
Total running time:  2:12:55.015976
