==========
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_small', pretrained_path='/home/ma-user/work/Projects/ReIDNets_Checkpoints_TransReID/ViT_Small_P16_2468_406080100_bs96_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_small_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.
optimizer: SGD
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.268 (0.350)	Data 0.133 (0.064)	
Extract Features: [100/128]	Time 0.128 (0.259)	Data 0.000 (0.050)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.79979968070984
Clustering criterion: eps: 0.700
==> Statistics for epoch 0: 841 clusters
Epoch: [0][20/200]	Time 0.384 (1.284)	Data 0.000 (0.047)	Loss 1.830 (3.268)
Epoch: [0][40/200]	Time 0.385 (0.871)	Data 0.001 (0.061)	Loss 4.506 (3.461)
Epoch: [0][60/200]	Time 0.384 (0.735)	Data 0.001 (0.065)	Loss 3.308 (3.538)
Epoch: [0][80/200]	Time 0.378 (0.665)	Data 0.000 (0.067)	Loss 2.603 (3.354)
Epoch: [0][100/200]	Time 0.384 (0.609)	Data 0.000 (0.054)	Loss 2.267 (3.161)
Epoch: [0][120/200]	Time 0.382 (0.585)	Data 0.001 (0.058)	Loss 2.922 (3.033)
Epoch: [0][140/200]	Time 0.382 (0.567)	Data 0.001 (0.060)	Loss 2.018 (2.901)
Epoch: [0][160/200]	Time 0.381 (0.553)	Data 0.001 (0.061)	Loss 2.287 (2.817)
Epoch: [0][180/200]	Time 0.392 (0.534)	Data 0.000 (0.055)	Loss 2.149 (2.728)
Epoch: [0][200/200]	Time 0.386 (0.527)	Data 0.001 (0.057)	Loss 1.785 (2.651)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.209)	Data 0.000 (0.078)	
Extract Features: [100/128]	Time 0.127 (0.191)	Data 0.001 (0.059)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.505213260650635
==> Statistics for epoch 1: 905 clusters
Epoch: [1][20/200]	Time 0.383 (0.440)	Data 0.001 (0.057)	Loss 0.460 (0.522)
Epoch: [1][40/200]	Time 0.382 (0.451)	Data 0.001 (0.069)	Loss 2.160 (0.967)
Epoch: [1][60/200]	Time 0.532 (0.457)	Data 0.001 (0.072)	Loss 1.880 (1.314)
Epoch: [1][80/200]	Time 0.379 (0.439)	Data 0.000 (0.054)	Loss 1.941 (1.494)
Epoch: [1][100/200]	Time 0.384 (0.444)	Data 0.000 (0.059)	Loss 2.042 (1.607)
Epoch: [1][120/200]	Time 0.385 (0.449)	Data 0.001 (0.063)	Loss 1.930 (1.660)
Epoch: [1][140/200]	Time 0.380 (0.440)	Data 0.000 (0.054)	Loss 2.380 (1.699)
Epoch: [1][160/200]	Time 0.402 (0.443)	Data 0.001 (0.057)	Loss 1.920 (1.727)
Epoch: [1][180/200]	Time 0.384 (0.446)	Data 0.000 (0.060)	Loss 2.085 (1.749)
Epoch: [1][200/200]	Time 0.388 (0.447)	Data 0.001 (0.061)	Loss 2.332 (1.758)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.522 (0.219)	Data 0.262 (0.088)	
Extract Features: [100/128]	Time 0.128 (0.194)	Data 0.000 (0.065)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.5177788734436
==> Statistics for epoch 2: 910 clusters
Epoch: [2][20/200]	Time 0.385 (0.434)	Data 0.001 (0.054)	Loss 0.406 (0.479)
Epoch: [2][40/200]	Time 0.380 (0.450)	Data 0.001 (0.069)	Loss 2.039 (0.861)
Epoch: [2][60/200]	Time 0.375 (0.455)	Data 0.001 (0.073)	Loss 2.351 (1.203)
Epoch: [2][80/200]	Time 0.383 (0.437)	Data 0.000 (0.055)	Loss 2.499 (1.362)
Epoch: [2][100/200]	Time 0.382 (0.444)	Data 0.001 (0.060)	Loss 2.179 (1.465)
Epoch: [2][120/200]	Time 0.378 (0.448)	Data 0.001 (0.064)	Loss 2.126 (1.533)
Epoch: [2][140/200]	Time 0.383 (0.439)	Data 0.000 (0.055)	Loss 2.397 (1.581)
Epoch: [2][160/200]	Time 0.382 (0.443)	Data 0.001 (0.058)	Loss 2.476 (1.616)
Epoch: [2][180/200]	Time 0.390 (0.445)	Data 0.001 (0.060)	Loss 1.518 (1.636)
Epoch: [2][200/200]	Time 0.383 (0.447)	Data 0.001 (0.062)	Loss 1.822 (1.647)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.164 (0.205)	Data 0.036 (0.077)	
Extract Features: [100/128]	Time 0.307 (0.192)	Data 0.180 (0.063)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.22834801673889
==> Statistics for epoch 3: 985 clusters
Epoch: [3][20/200]	Time 0.377 (0.428)	Data 0.001 (0.046)	Loss 0.268 (0.435)
Epoch: [3][40/200]	Time 0.375 (0.443)	Data 0.001 (0.060)	Loss 1.582 (0.760)
Epoch: [3][60/200]	Time 0.383 (0.423)	Data 0.000 (0.040)	Loss 1.618 (1.120)
Epoch: [3][80/200]	Time 0.385 (0.434)	Data 0.001 (0.050)	Loss 2.073 (1.283)
Epoch: [3][100/200]	Time 0.387 (0.441)	Data 0.001 (0.057)	Loss 1.530 (1.422)
Epoch: [3][120/200]	Time 0.385 (0.431)	Data 0.000 (0.047)	Loss 2.156 (1.500)
Epoch: [3][140/200]	Time 0.384 (0.436)	Data 0.001 (0.052)	Loss 2.152 (1.552)
Epoch: [3][160/200]	Time 0.379 (0.440)	Data 0.001 (0.056)	Loss 1.807 (1.578)
Epoch: [3][180/200]	Time 0.384 (0.434)	Data 0.000 (0.050)	Loss 2.335 (1.613)
Epoch: [3][200/200]	Time 0.393 (0.436)	Data 0.001 (0.052)	Loss 1.762 (1.624)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.127 (0.210)	Data 0.000 (0.080)	
Extract Features: [100/128]	Time 0.128 (0.191)	Data 0.000 (0.061)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.2312593460083
==> Statistics for epoch 4: 990 clusters
Epoch: [4][20/200]	Time 0.380 (0.431)	Data 0.001 (0.050)	Loss 0.419 (0.494)
Epoch: [4][40/200]	Time 0.382 (0.448)	Data 0.001 (0.066)	Loss 2.000 (0.779)
Epoch: [4][60/200]	Time 0.381 (0.428)	Data 0.000 (0.044)	Loss 1.663 (1.131)
Epoch: [4][80/200]	Time 0.385 (0.438)	Data 0.001 (0.053)	Loss 2.037 (1.337)
Epoch: [4][100/200]	Time 0.394 (0.442)	Data 0.001 (0.058)	Loss 2.082 (1.453)
Epoch: [4][120/200]	Time 0.387 (0.434)	Data 0.000 (0.048)	Loss 1.850 (1.537)
Epoch: [4][140/200]	Time 0.386 (0.438)	Data 0.001 (0.053)	Loss 1.691 (1.584)
Epoch: [4][160/200]	Time 0.388 (0.441)	Data 0.001 (0.056)	Loss 1.425 (1.624)
Epoch: [4][180/200]	Time 0.386 (0.435)	Data 0.000 (0.050)	Loss 1.589 (1.649)
Epoch: [4][200/200]	Time 0.380 (0.438)	Data 0.001 (0.053)	Loss 1.674 (1.668)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.169 (0.212)	Data 0.041 (0.081)	
Extract Features: [100/128]	Time 0.127 (0.192)	Data 0.000 (0.063)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.8238046169281
==> Statistics for epoch 5: 964 clusters
Epoch: [5][20/200]	Time 0.379 (0.430)	Data 0.001 (0.048)	Loss 0.480 (0.457)
Epoch: [5][40/200]	Time 0.384 (0.443)	Data 0.001 (0.061)	Loss 1.666 (0.794)
Epoch: [5][60/200]	Time 0.382 (0.422)	Data 0.000 (0.041)	Loss 1.285 (1.141)
Epoch: [5][80/200]	Time 0.385 (0.432)	Data 0.001 (0.051)	Loss 2.229 (1.338)
Epoch: [5][100/200]	Time 0.382 (0.442)	Data 0.001 (0.059)	Loss 2.055 (1.434)
Epoch: [5][120/200]	Time 0.377 (0.432)	Data 0.000 (0.049)	Loss 1.804 (1.496)
Epoch: [5][140/200]	Time 0.384 (0.436)	Data 0.001 (0.054)	Loss 1.438 (1.552)
Epoch: [5][160/200]	Time 0.384 (0.440)	Data 0.001 (0.057)	Loss 1.529 (1.577)
Epoch: [5][180/200]	Time 0.379 (0.435)	Data 0.000 (0.051)	Loss 1.915 (1.608)
Epoch: [5][200/200]	Time 0.388 (0.438)	Data 0.001 (0.054)	Loss 1.536 (1.626)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.214)	Data 0.000 (0.084)	
Extract Features: [100/128]	Time 0.128 (0.195)	Data 0.000 (0.067)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.0920307636261
==> Statistics for epoch 6: 964 clusters
Epoch: [6][20/200]	Time 0.389 (0.442)	Data 0.001 (0.055)	Loss 0.444 (0.423)
Epoch: [6][40/200]	Time 0.385 (0.453)	Data 0.001 (0.068)	Loss 1.628 (0.732)
Epoch: [6][60/200]	Time 0.385 (0.429)	Data 0.000 (0.045)	Loss 1.666 (1.075)
Epoch: [6][80/200]	Time 0.377 (0.437)	Data 0.001 (0.053)	Loss 1.611 (1.256)
Epoch: [6][100/200]	Time 0.374 (0.442)	Data 0.000 (0.058)	Loss 2.303 (1.373)
Epoch: [6][120/200]	Time 0.378 (0.432)	Data 0.000 (0.049)	Loss 1.569 (1.452)
Epoch: [6][140/200]	Time 0.379 (0.435)	Data 0.000 (0.052)	Loss 1.774 (1.499)
Epoch: [6][160/200]	Time 0.381 (0.438)	Data 0.000 (0.055)	Loss 1.701 (1.527)
Epoch: [6][180/200]	Time 0.386 (0.432)	Data 0.000 (0.049)	Loss 1.804 (1.563)
Epoch: [6][200/200]	Time 0.385 (0.435)	Data 0.000 (0.051)	Loss 1.905 (1.568)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.210)	Data 0.000 (0.080)	
Extract Features: [100/128]	Time 0.128 (0.191)	Data 0.001 (0.060)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.53994965553284
==> Statistics for epoch 7: 983 clusters
Epoch: [7][20/200]	Time 0.379 (0.434)	Data 0.001 (0.053)	Loss 0.310 (0.401)
Epoch: [7][40/200]	Time 0.380 (0.446)	Data 0.001 (0.065)	Loss 1.284 (0.707)
Epoch: [7][60/200]	Time 0.385 (0.426)	Data 0.000 (0.044)	Loss 2.248 (1.080)
Epoch: [7][80/200]	Time 0.385 (0.435)	Data 0.000 (0.053)	Loss 1.652 (1.253)
Epoch: [7][100/200]	Time 0.385 (0.441)	Data 0.001 (0.058)	Loss 1.967 (1.384)
Epoch: [7][120/200]	Time 0.387 (0.431)	Data 0.000 (0.048)	Loss 1.404 (1.457)
Epoch: [7][140/200]	Time 0.383 (0.436)	Data 0.001 (0.053)	Loss 1.602 (1.490)
Epoch: [7][160/200]	Time 0.387 (0.438)	Data 0.001 (0.055)	Loss 1.651 (1.549)
Epoch: [7][180/200]	Time 0.384 (0.432)	Data 0.000 (0.049)	Loss 2.162 (1.571)
Epoch: [7][200/200]	Time 0.384 (0.436)	Data 0.001 (0.052)	Loss 1.856 (1.597)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.131 (0.213)	Data 0.000 (0.085)	
Extract Features: [100/128]	Time 0.127 (0.191)	Data 0.000 (0.062)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.24138331413269
==> Statistics for epoch 8: 983 clusters
Epoch: [8][20/200]	Time 0.377 (0.429)	Data 0.000 (0.047)	Loss 0.732 (0.436)
Epoch: [8][40/200]	Time 0.390 (0.446)	Data 0.001 (0.062)	Loss 1.504 (0.762)
Epoch: [8][60/200]	Time 0.381 (0.424)	Data 0.000 (0.041)	Loss 1.671 (1.097)
Epoch: [8][80/200]	Time 0.386 (0.434)	Data 0.001 (0.050)	Loss 1.922 (1.297)
Epoch: [8][100/200]	Time 0.385 (0.439)	Data 0.000 (0.055)	Loss 2.344 (1.391)
Epoch: [8][120/200]	Time 0.380 (0.429)	Data 0.000 (0.046)	Loss 1.383 (1.459)
Epoch: [8][140/200]	Time 0.385 (0.434)	Data 0.000 (0.051)	Loss 1.804 (1.494)
Epoch: [8][160/200]	Time 0.377 (0.438)	Data 0.001 (0.055)	Loss 2.067 (1.540)
Epoch: [8][180/200]	Time 0.386 (0.432)	Data 0.000 (0.049)	Loss 1.533 (1.565)
Epoch: [8][200/200]	Time 0.386 (0.435)	Data 0.000 (0.051)	Loss 1.969 (1.596)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.127 (0.211)	Data 0.000 (0.081)	
Extract Features: [100/128]	Time 0.128 (0.190)	Data 0.000 (0.060)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.137900829315186
==> Statistics for epoch 9: 970 clusters
Epoch: [9][20/200]	Time 0.373 (0.439)	Data 0.001 (0.050)	Loss 0.324 (0.425)
Epoch: [9][40/200]	Time 0.383 (0.453)	Data 0.001 (0.067)	Loss 1.560 (0.683)
Epoch: [9][60/200]	Time 0.386 (0.429)	Data 0.000 (0.045)	Loss 1.978 (1.072)
Epoch: [9][80/200]	Time 0.385 (0.439)	Data 0.001 (0.054)	Loss 1.517 (1.222)
Epoch: [9][100/200]	Time 0.386 (0.445)	Data 0.001 (0.060)	Loss 1.322 (1.338)
Epoch: [9][120/200]	Time 0.380 (0.435)	Data 0.000 (0.050)	Loss 2.055 (1.418)
Epoch: [9][140/200]	Time 0.385 (0.439)	Data 0.001 (0.054)	Loss 1.615 (1.463)
Epoch: [9][160/200]	Time 0.390 (0.443)	Data 0.001 (0.058)	Loss 1.906 (1.506)
Epoch: [9][180/200]	Time 0.388 (0.436)	Data 0.000 (0.052)	Loss 1.442 (1.524)
Epoch: [9][200/200]	Time 0.385 (0.440)	Data 0.000 (0.055)	Loss 2.133 (1.551)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.212)	Data 0.000 (0.081)	
Extract Features: [100/128]	Time 0.128 (0.192)	Data 0.000 (0.063)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.27268099784851
==> Statistics for epoch 10: 987 clusters
Epoch: [10][20/200]	Time 0.378 (0.437)	Data 0.001 (0.055)	Loss 0.500 (0.377)
Epoch: [10][40/200]	Time 0.385 (0.452)	Data 0.001 (0.070)	Loss 1.591 (0.709)
Epoch: [10][60/200]	Time 0.378 (0.429)	Data 0.000 (0.047)	Loss 1.254 (1.024)
Epoch: [10][80/200]	Time 0.387 (0.437)	Data 0.001 (0.054)	Loss 1.425 (1.189)
Epoch: [10][100/200]	Time 0.378 (0.442)	Data 0.001 (0.059)	Loss 1.711 (1.296)
Epoch: [10][120/200]	Time 0.384 (0.433)	Data 0.000 (0.049)	Loss 2.187 (1.383)
Epoch: [10][140/200]	Time 0.384 (0.437)	Data 0.001 (0.053)	Loss 1.800 (1.431)
Epoch: [10][160/200]	Time 0.383 (0.441)	Data 0.001 (0.057)	Loss 2.053 (1.468)
Epoch: [10][180/200]	Time 0.383 (0.435)	Data 0.000 (0.051)	Loss 1.387 (1.499)
Epoch: [10][200/200]	Time 0.380 (0.438)	Data 0.001 (0.053)	Loss 2.168 (1.522)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.212)	Data 0.000 (0.081)	
Extract Features: [100/128]	Time 0.127 (0.191)	Data 0.000 (0.061)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.264216899871826
==> Statistics for epoch 11: 986 clusters
Epoch: [11][20/200]	Time 0.371 (0.435)	Data 0.001 (0.054)	Loss 0.288 (0.378)
Epoch: [11][40/200]	Time 0.380 (0.449)	Data 0.001 (0.069)	Loss 1.316 (0.680)
Epoch: [11][60/200]	Time 0.382 (0.429)	Data 0.000 (0.046)	Loss 1.602 (1.013)
Epoch: [11][80/200]	Time 0.387 (0.437)	Data 0.001 (0.054)	Loss 1.603 (1.182)
Epoch: [11][100/200]	Time 0.382 (0.443)	Data 0.001 (0.060)	Loss 1.254 (1.297)
Epoch: [11][120/200]	Time 0.380 (0.433)	Data 0.000 (0.050)	Loss 1.710 (1.385)
Epoch: [11][140/200]	Time 0.386 (0.437)	Data 0.001 (0.053)	Loss 1.540 (1.431)
Epoch: [11][160/200]	Time 0.382 (0.440)	Data 0.001 (0.057)	Loss 1.612 (1.471)
Epoch: [11][180/200]	Time 0.381 (0.434)	Data 0.000 (0.050)	Loss 1.490 (1.500)
Epoch: [11][200/200]	Time 0.382 (0.436)	Data 0.001 (0.053)	Loss 1.983 (1.521)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.159 (0.208)	Data 0.035 (0.077)	
Extract Features: [100/128]	Time 0.127 (0.190)	Data 0.000 (0.059)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.70895552635193
==> Statistics for epoch 12: 1007 clusters
Epoch: [12][20/200]	Time 0.381 (0.431)	Data 0.000 (0.050)	Loss 0.458 (0.381)
Epoch: [12][40/200]	Time 0.380 (0.444)	Data 0.001 (0.064)	Loss 1.773 (0.661)
Epoch: [12][60/200]	Time 0.382 (0.423)	Data 0.000 (0.043)	Loss 2.253 (1.014)
Epoch: [12][80/200]	Time 0.380 (0.432)	Data 0.001 (0.051)	Loss 1.705 (1.172)
Epoch: [12][100/200]	Time 0.383 (0.437)	Data 0.001 (0.055)	Loss 2.089 (1.275)
Epoch: [12][120/200]	Time 0.377 (0.428)	Data 0.000 (0.046)	Loss 1.680 (1.364)
Epoch: [12][140/200]	Time 0.380 (0.433)	Data 0.000 (0.051)	Loss 1.524 (1.415)
Epoch: [12][160/200]	Time 0.378 (0.437)	Data 0.001 (0.054)	Loss 1.443 (1.452)
Epoch: [12][180/200]	Time 0.386 (0.431)	Data 0.000 (0.048)	Loss 1.626 (1.472)
Epoch: [12][200/200]	Time 0.383 (0.435)	Data 0.001 (0.051)	Loss 2.129 (1.495)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.127 (0.214)	Data 0.000 (0.084)	
Extract Features: [100/128]	Time 0.129 (0.194)	Data 0.001 (0.064)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.25766468048096
==> Statistics for epoch 13: 970 clusters
Epoch: [13][20/200]	Time 0.383 (0.430)	Data 0.001 (0.050)	Loss 0.290 (0.351)
Epoch: [13][40/200]	Time 0.376 (0.445)	Data 0.001 (0.065)	Loss 1.266 (0.647)
Epoch: [13][60/200]	Time 0.382 (0.426)	Data 0.000 (0.043)	Loss 2.137 (0.967)
Epoch: [13][80/200]	Time 0.379 (0.434)	Data 0.001 (0.052)	Loss 2.160 (1.128)
Epoch: [13][100/200]	Time 0.381 (0.440)	Data 0.000 (0.058)	Loss 1.772 (1.210)
Epoch: [13][120/200]	Time 0.382 (0.431)	Data 0.000 (0.048)	Loss 1.893 (1.280)
Epoch: [13][140/200]	Time 0.386 (0.436)	Data 0.000 (0.053)	Loss 1.451 (1.325)
Epoch: [13][160/200]	Time 0.385 (0.439)	Data 0.001 (0.056)	Loss 1.494 (1.357)
Epoch: [13][180/200]	Time 0.383 (0.433)	Data 0.000 (0.050)	Loss 1.534 (1.378)
Epoch: [13][200/200]	Time 0.387 (0.436)	Data 0.001 (0.053)	Loss 1.248 (1.399)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.366 (0.211)	Data 0.243 (0.081)	
Extract Features: [100/128]	Time 0.127 (0.193)	Data 0.000 (0.064)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.807661294937134
==> Statistics for epoch 14: 979 clusters
Epoch: [14][20/200]	Time 0.376 (0.431)	Data 0.001 (0.049)	Loss 0.319 (0.368)
Epoch: [14][40/200]	Time 0.384 (0.446)	Data 0.001 (0.065)	Loss 1.510 (0.668)
Epoch: [14][60/200]	Time 0.384 (0.424)	Data 0.000 (0.043)	Loss 1.928 (0.988)
Epoch: [14][80/200]	Time 0.385 (0.432)	Data 0.001 (0.051)	Loss 1.416 (1.136)
Epoch: [14][100/200]	Time 0.387 (0.439)	Data 0.001 (0.057)	Loss 1.301 (1.253)
Epoch: [14][120/200]	Time 0.385 (0.430)	Data 0.000 (0.047)	Loss 1.673 (1.327)
Epoch: [14][140/200]	Time 0.385 (0.435)	Data 0.001 (0.052)	Loss 1.333 (1.361)
Epoch: [14][160/200]	Time 0.383 (0.439)	Data 0.001 (0.055)	Loss 1.489 (1.396)
Epoch: [14][180/200]	Time 0.387 (0.433)	Data 0.000 (0.049)	Loss 1.546 (1.425)
Epoch: [14][200/200]	Time 0.387 (0.437)	Data 0.001 (0.052)	Loss 1.439 (1.445)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.214)	Data 0.000 (0.083)	
Extract Features: [100/128]	Time 0.127 (0.192)	Data 0.000 (0.063)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.592074394226074
==> Statistics for epoch 15: 999 clusters
Epoch: [15][20/200]	Time 0.382 (0.433)	Data 0.001 (0.051)	Loss 0.199 (0.342)
Epoch: [15][40/200]	Time 0.383 (0.447)	Data 0.001 (0.065)	Loss 1.740 (0.624)
Epoch: [15][60/200]	Time 0.384 (0.425)	Data 0.000 (0.043)	Loss 1.658 (0.958)
Epoch: [15][80/200]	Time 0.386 (0.435)	Data 0.001 (0.053)	Loss 1.563 (1.143)
Epoch: [15][100/200]	Time 0.383 (0.442)	Data 0.001 (0.059)	Loss 1.342 (1.220)
Epoch: [15][120/200]	Time 0.392 (0.432)	Data 0.000 (0.049)	Loss 1.385 (1.289)
Epoch: [15][140/200]	Time 0.396 (0.437)	Data 0.001 (0.054)	Loss 1.598 (1.320)
Epoch: [15][160/200]	Time 0.388 (0.441)	Data 0.000 (0.057)	Loss 1.379 (1.356)
Epoch: [15][180/200]	Time 0.385 (0.434)	Data 0.000 (0.051)	Loss 2.198 (1.382)
Epoch: [15][200/200]	Time 0.389 (0.438)	Data 0.001 (0.054)	Loss 1.777 (1.402)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.125 (0.209)	Data 0.000 (0.082)	
Extract Features: [100/128]	Time 0.251 (0.190)	Data 0.000 (0.061)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.57676458358765
==> Statistics for epoch 16: 994 clusters
Epoch: [16][20/200]	Time 0.382 (0.428)	Data 0.001 (0.048)	Loss 0.381 (0.311)
Epoch: [16][40/200]	Time 0.381 (0.442)	Data 0.000 (0.062)	Loss 2.034 (0.606)
Epoch: [16][60/200]	Time 0.378 (0.422)	Data 0.000 (0.041)	Loss 1.839 (0.924)
Epoch: [16][80/200]	Time 0.384 (0.432)	Data 0.001 (0.051)	Loss 1.037 (1.093)
Epoch: [16][100/200]	Time 0.382 (0.439)	Data 0.000 (0.057)	Loss 1.555 (1.180)
Epoch: [16][120/200]	Time 0.382 (0.430)	Data 0.000 (0.048)	Loss 1.355 (1.242)
Epoch: [16][140/200]	Time 0.380 (0.435)	Data 0.001 (0.052)	Loss 1.768 (1.294)
Epoch: [16][160/200]	Time 0.379 (0.439)	Data 0.001 (0.056)	Loss 1.636 (1.328)
Epoch: [16][180/200]	Time 0.378 (0.432)	Data 0.000 (0.050)	Loss 1.689 (1.349)
Epoch: [16][200/200]	Time 0.386 (0.435)	Data 0.001 (0.053)	Loss 1.485 (1.372)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.127 (0.213)	Data 0.000 (0.082)	
Extract Features: [100/128]	Time 0.129 (0.194)	Data 0.000 (0.063)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.15707874298096
==> Statistics for epoch 17: 1001 clusters
Epoch: [17][20/200]	Time 0.374 (0.430)	Data 0.001 (0.048)	Loss 0.260 (0.333)
Epoch: [17][40/200]	Time 0.385 (0.445)	Data 0.001 (0.062)	Loss 2.063 (0.574)
Epoch: [17][60/200]	Time 0.382 (0.424)	Data 0.000 (0.042)	Loss 1.400 (0.912)
Epoch: [17][80/200]	Time 0.386 (0.434)	Data 0.001 (0.050)	Loss 1.436 (1.064)
Epoch: [17][100/200]	Time 0.387 (0.440)	Data 0.001 (0.056)	Loss 1.695 (1.160)
Epoch: [17][120/200]	Time 0.384 (0.431)	Data 0.000 (0.047)	Loss 1.702 (1.235)
Epoch: [17][140/200]	Time 0.376 (0.436)	Data 0.000 (0.052)	Loss 1.537 (1.285)
Epoch: [17][160/200]	Time 0.386 (0.440)	Data 0.001 (0.056)	Loss 2.453 (1.322)
Epoch: [17][180/200]	Time 0.386 (0.434)	Data 0.000 (0.049)	Loss 1.486 (1.356)
Epoch: [17][200/200]	Time 0.381 (0.437)	Data 0.000 (0.053)	Loss 1.329 (1.370)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.129 (0.207)	Data 0.000 (0.077)	
Extract Features: [100/128]	Time 0.128 (0.189)	Data 0.000 (0.059)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.03857946395874
==> Statistics for epoch 18: 980 clusters
Epoch: [18][20/200]	Time 0.372 (0.431)	Data 0.001 (0.051)	Loss 0.348 (0.311)
Epoch: [18][40/200]	Time 0.381 (0.444)	Data 0.001 (0.063)	Loss 1.248 (0.563)
Epoch: [18][60/200]	Time 0.382 (0.425)	Data 0.000 (0.042)	Loss 1.661 (0.902)
Epoch: [18][80/200]	Time 0.383 (0.434)	Data 0.001 (0.051)	Loss 1.138 (1.045)
Epoch: [18][100/200]	Time 0.383 (0.440)	Data 0.001 (0.057)	Loss 1.340 (1.149)
Epoch: [18][120/200]	Time 0.383 (0.430)	Data 0.000 (0.047)	Loss 1.390 (1.205)
Epoch: [18][140/200]	Time 0.379 (0.435)	Data 0.000 (0.052)	Loss 1.279 (1.245)
Epoch: [18][160/200]	Time 0.380 (0.439)	Data 0.001 (0.056)	Loss 1.339 (1.283)
Epoch: [18][180/200]	Time 0.376 (0.433)	Data 0.000 (0.050)	Loss 1.236 (1.315)
Epoch: [18][200/200]	Time 0.384 (0.435)	Data 0.001 (0.052)	Loss 2.149 (1.335)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.127 (0.212)	Data 0.000 (0.082)	
Extract Features: [100/128]	Time 0.129 (0.193)	Data 0.000 (0.062)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.46043252944946
==> Statistics for epoch 19: 1026 clusters
Epoch: [19][20/200]	Time 0.380 (0.437)	Data 0.001 (0.056)	Loss 0.245 (0.291)
Epoch: [19][40/200]	Time 0.391 (0.448)	Data 0.001 (0.065)	Loss 1.706 (0.508)
Epoch: [19][60/200]	Time 0.380 (0.429)	Data 0.000 (0.044)	Loss 1.564 (0.848)
Epoch: [19][80/200]	Time 0.379 (0.439)	Data 0.001 (0.054)	Loss 1.539 (1.017)
Epoch: [19][100/200]	Time 0.377 (0.444)	Data 0.000 (0.060)	Loss 1.571 (1.126)
Epoch: [19][120/200]	Time 0.382 (0.434)	Data 0.001 (0.050)	Loss 1.430 (1.191)
Epoch: [19][140/200]	Time 0.387 (0.438)	Data 0.000 (0.054)	Loss 1.319 (1.251)
Epoch: [19][160/200]	Time 0.381 (0.432)	Data 0.000 (0.048)	Loss 1.559 (1.289)
Epoch: [19][180/200]	Time 0.383 (0.435)	Data 0.000 (0.050)	Loss 1.607 (1.311)
Epoch: [19][200/200]	Time 0.390 (0.437)	Data 0.000 (0.053)	Loss 1.619 (1.343)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.131 (0.207)	Data 0.000 (0.076)	
Extract Features: [100/128]	Time 0.128 (0.192)	Data 0.000 (0.061)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.691645860672
==> Statistics for epoch 20: 1005 clusters
Epoch: [20][20/200]	Time 0.379 (0.435)	Data 0.001 (0.054)	Loss 0.229 (0.290)
Epoch: [20][40/200]	Time 0.375 (0.447)	Data 0.001 (0.065)	Loss 1.784 (0.549)
Epoch: [20][60/200]	Time 0.381 (0.427)	Data 0.000 (0.044)	Loss 1.343 (0.838)
Epoch: [20][80/200]	Time 0.386 (0.436)	Data 0.000 (0.053)	Loss 1.216 (0.975)
Epoch: [20][100/200]	Time 0.380 (0.440)	Data 0.000 (0.057)	Loss 1.092 (1.076)
Epoch: [20][120/200]	Time 0.382 (0.432)	Data 0.000 (0.048)	Loss 1.685 (1.144)
Epoch: [20][140/200]	Time 0.390 (0.436)	Data 0.000 (0.052)	Loss 1.269 (1.192)
Epoch: [20][160/200]	Time 0.389 (0.439)	Data 0.000 (0.055)	Loss 1.596 (1.220)
Epoch: [20][180/200]	Time 0.394 (0.433)	Data 0.000 (0.049)	Loss 1.703 (1.244)
Epoch: [20][200/200]	Time 0.392 (0.435)	Data 0.000 (0.051)	Loss 1.627 (1.252)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.129 (0.212)	Data 0.000 (0.082)	
Extract Features: [100/128]	Time 0.127 (0.192)	Data 0.000 (0.063)	
Computing jaccard distance...
Jaccard distance computing time cost: 57.9021360874176
==> Statistics for epoch 21: 1016 clusters
Epoch: [21][20/200]	Time 0.382 (0.431)	Data 0.001 (0.050)	Loss 0.272 (0.258)
Epoch: [21][40/200]	Time 0.384 (0.447)	Data 0.001 (0.066)	Loss 1.289 (0.498)
Epoch: [21][60/200]	Time 0.383 (0.425)	Data 0.000 (0.044)	Loss 1.399 (0.826)
Epoch: [21][80/200]	Time 0.377 (0.435)	Data 0.001 (0.051)	Loss 1.885 (0.980)
Epoch: [21][100/200]	Time 0.383 (0.441)	Data 0.001 (0.058)	Loss 1.774 (1.075)
Epoch: [21][120/200]	Time 0.382 (0.432)	Data 0.000 (0.048)	Loss 1.446 (1.137)
Epoch: [21][140/200]	Time 0.383 (0.437)	Data 0.001 (0.053)	Loss 1.530 (1.186)
Epoch: [21][160/200]	Time 0.389 (0.440)	Data 0.001 (0.056)	Loss 1.617 (1.210)
Epoch: [21][180/200]	Time 0.374 (0.434)	Data 0.000 (0.050)	Loss 1.435 (1.233)
Epoch: [21][200/200]	Time 0.386 (0.437)	Data 0.001 (0.053)	Loss 1.628 (1.257)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.133 (0.210)	Data 0.000 (0.080)	
Extract Features: [100/128]	Time 0.127 (0.195)	Data 0.000 (0.064)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.06017851829529
==> Statistics for epoch 22: 1024 clusters
Epoch: [22][20/200]	Time 0.377 (0.439)	Data 0.001 (0.057)	Loss 0.130 (0.290)
Epoch: [22][40/200]	Time 0.381 (0.448)	Data 0.001 (0.066)	Loss 1.584 (0.490)
Epoch: [22][60/200]	Time 0.378 (0.426)	Data 0.000 (0.044)	Loss 0.986 (0.790)
Epoch: [22][80/200]	Time 0.385 (0.438)	Data 0.001 (0.055)	Loss 1.303 (0.952)
Epoch: [22][100/200]	Time 0.386 (0.442)	Data 0.001 (0.059)	Loss 1.430 (1.043)
Epoch: [22][120/200]	Time 0.375 (0.432)	Data 0.001 (0.049)	Loss 1.258 (1.112)
Epoch: [22][140/200]	Time 0.387 (0.436)	Data 0.001 (0.053)	Loss 1.461 (1.166)
Epoch: [22][160/200]	Time 0.380 (0.430)	Data 0.000 (0.046)	Loss 2.118 (1.203)
Epoch: [22][180/200]	Time 0.383 (0.434)	Data 0.000 (0.050)	Loss 1.535 (1.233)
Epoch: [22][200/200]	Time 0.377 (0.438)	Data 0.000 (0.053)	Loss 1.373 (1.256)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.362 (0.210)	Data 0.236 (0.080)	
Extract Features: [100/128]	Time 0.131 (0.190)	Data 0.001 (0.061)	
Computing jaccard distance...
Jaccard distance computing time cost: 57.91948914527893
==> Statistics for epoch 23: 1019 clusters
Epoch: [23][20/200]	Time 0.379 (0.437)	Data 0.001 (0.054)	Loss 0.223 (0.244)
Epoch: [23][40/200]	Time 0.379 (0.447)	Data 0.000 (0.066)	Loss 1.054 (0.485)
Epoch: [23][60/200]	Time 0.384 (0.426)	Data 0.000 (0.044)	Loss 1.564 (0.767)
Epoch: [23][80/200]	Time 0.378 (0.434)	Data 0.001 (0.053)	Loss 1.621 (0.907)
Epoch: [23][100/200]	Time 0.379 (0.439)	Data 0.001 (0.057)	Loss 1.543 (1.003)
Epoch: [23][120/200]	Time 0.381 (0.429)	Data 0.000 (0.047)	Loss 1.159 (1.060)
Epoch: [23][140/200]	Time 0.383 (0.434)	Data 0.001 (0.052)	Loss 1.145 (1.118)
Epoch: [23][160/200]	Time 0.390 (0.437)	Data 0.001 (0.055)	Loss 1.109 (1.154)
Epoch: [23][180/200]	Time 0.377 (0.431)	Data 0.000 (0.049)	Loss 1.609 (1.177)
Epoch: [23][200/200]	Time 0.378 (0.435)	Data 0.000 (0.052)	Loss 1.145 (1.203)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.214)	Data 0.000 (0.087)	
Extract Features: [100/128]	Time 0.127 (0.198)	Data 0.000 (0.069)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.87740111351013
==> Statistics for epoch 24: 1012 clusters
Epoch: [24][20/200]	Time 0.385 (0.438)	Data 0.001 (0.055)	Loss 0.213 (0.241)
Epoch: [24][40/200]	Time 0.377 (0.451)	Data 0.000 (0.066)	Loss 1.190 (0.465)
Epoch: [24][60/200]	Time 0.381 (0.428)	Data 0.000 (0.044)	Loss 1.308 (0.757)
Epoch: [24][80/200]	Time 0.385 (0.438)	Data 0.001 (0.053)	Loss 1.463 (0.902)
Epoch: [24][100/200]	Time 0.388 (0.444)	Data 0.001 (0.060)	Loss 1.530 (1.003)
Epoch: [24][120/200]	Time 0.381 (0.434)	Data 0.000 (0.050)	Loss 1.606 (1.067)
Epoch: [24][140/200]	Time 0.383 (0.439)	Data 0.001 (0.054)	Loss 1.725 (1.114)
Epoch: [24][160/200]	Time 0.382 (0.443)	Data 0.001 (0.058)	Loss 1.046 (1.145)
Epoch: [24][180/200]	Time 0.374 (0.436)	Data 0.000 (0.052)	Loss 1.211 (1.169)
Epoch: [24][200/200]	Time 0.382 (0.439)	Data 0.001 (0.055)	Loss 1.298 (1.191)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.134 (0.207)	Data 0.007 (0.077)	
Extract Features: [100/128]	Time 0.126 (0.193)	Data 0.000 (0.063)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.67363214492798
==> Statistics for epoch 25: 1030 clusters
Epoch: [25][20/200]	Time 0.381 (0.434)	Data 0.001 (0.052)	Loss 0.173 (0.293)
Epoch: [25][40/200]	Time 0.388 (0.445)	Data 0.001 (0.063)	Loss 1.732 (0.492)
Epoch: [25][60/200]	Time 0.378 (0.426)	Data 0.000 (0.042)	Loss 1.501 (0.817)
Epoch: [25][80/200]	Time 0.388 (0.435)	Data 0.001 (0.051)	Loss 1.520 (0.935)
Epoch: [25][100/200]	Time 0.375 (0.440)	Data 0.001 (0.057)	Loss 1.356 (1.042)
Epoch: [25][120/200]	Time 0.384 (0.431)	Data 0.001 (0.047)	Loss 1.715 (1.107)
Epoch: [25][140/200]	Time 0.388 (0.436)	Data 0.001 (0.052)	Loss 1.456 (1.150)
Epoch: [25][160/200]	Time 0.380 (0.429)	Data 0.000 (0.045)	Loss 1.179 (1.181)
Epoch: [25][180/200]	Time 0.381 (0.434)	Data 0.001 (0.049)	Loss 1.667 (1.210)
Epoch: [25][200/200]	Time 0.376 (0.438)	Data 0.001 (0.053)	Loss 1.555 (1.234)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.129 (0.203)	Data 0.000 (0.075)	
Extract Features: [100/128]	Time 0.128 (0.186)	Data 0.000 (0.057)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.43939280509949
==> Statistics for epoch 26: 1022 clusters
Epoch: [26][20/200]	Time 0.383 (0.437)	Data 0.001 (0.056)	Loss 0.214 (0.240)
Epoch: [26][40/200]	Time 0.379 (0.449)	Data 0.001 (0.069)	Loss 1.587 (0.503)
Epoch: [26][60/200]	Time 0.376 (0.426)	Data 0.000 (0.046)	Loss 1.038 (0.761)
Epoch: [26][80/200]	Time 0.385 (0.437)	Data 0.001 (0.055)	Loss 1.400 (0.905)
Epoch: [26][100/200]	Time 0.383 (0.442)	Data 0.000 (0.059)	Loss 1.351 (1.007)
Epoch: [26][120/200]	Time 0.381 (0.432)	Data 0.000 (0.049)	Loss 1.191 (1.087)
Epoch: [26][140/200]	Time 0.396 (0.438)	Data 0.000 (0.054)	Loss 1.216 (1.130)
Epoch: [26][160/200]	Time 0.382 (0.441)	Data 0.001 (0.057)	Loss 1.784 (1.171)
Epoch: [26][180/200]	Time 0.387 (0.435)	Data 0.000 (0.051)	Loss 1.383 (1.200)
Epoch: [26][200/200]	Time 0.399 (0.437)	Data 0.001 (0.053)	Loss 1.422 (1.221)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.212)	Data 0.000 (0.082)	
Extract Features: [100/128]	Time 0.239 (0.195)	Data 0.000 (0.065)	
Computing jaccard distance...
Jaccard distance computing time cost: 57.943702697753906
==> Statistics for epoch 27: 1021 clusters
Epoch: [27][20/200]	Time 0.378 (0.431)	Data 0.001 (0.049)	Loss 0.260 (0.271)
Epoch: [27][40/200]	Time 0.386 (0.443)	Data 0.001 (0.061)	Loss 1.471 (0.499)
Epoch: [27][60/200]	Time 0.377 (0.423)	Data 0.000 (0.041)	Loss 1.748 (0.806)
Epoch: [27][80/200]	Time 0.389 (0.432)	Data 0.001 (0.050)	Loss 1.109 (0.961)
Epoch: [27][100/200]	Time 0.384 (0.437)	Data 0.001 (0.055)	Loss 1.601 (1.043)
Epoch: [27][120/200]	Time 0.379 (0.428)	Data 0.000 (0.046)	Loss 1.528 (1.086)
Epoch: [27][140/200]	Time 0.381 (0.433)	Data 0.001 (0.050)	Loss 1.134 (1.152)
Epoch: [27][160/200]	Time 0.386 (0.437)	Data 0.001 (0.054)	Loss 1.472 (1.182)
Epoch: [27][180/200]	Time 0.383 (0.431)	Data 0.000 (0.048)	Loss 1.336 (1.202)
Epoch: [27][200/200]	Time 0.389 (0.434)	Data 0.001 (0.051)	Loss 1.224 (1.221)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.206)	Data 0.000 (0.076)	
Extract Features: [100/128]	Time 0.127 (0.188)	Data 0.000 (0.059)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.52529692649841
==> Statistics for epoch 28: 1017 clusters
Epoch: [28][20/200]	Time 0.377 (0.435)	Data 0.001 (0.054)	Loss 0.175 (0.245)
Epoch: [28][40/200]	Time 0.385 (0.451)	Data 0.001 (0.069)	Loss 1.325 (0.486)
Epoch: [28][60/200]	Time 0.380 (0.430)	Data 0.000 (0.046)	Loss 1.335 (0.773)
Epoch: [28][80/200]	Time 0.382 (0.438)	Data 0.001 (0.054)	Loss 1.678 (0.922)
Epoch: [28][100/200]	Time 0.382 (0.442)	Data 0.001 (0.059)	Loss 1.205 (1.032)
Epoch: [28][120/200]	Time 0.383 (0.433)	Data 0.000 (0.049)	Loss 1.447 (1.106)
Epoch: [28][140/200]	Time 0.386 (0.436)	Data 0.001 (0.053)	Loss 1.172 (1.150)
Epoch: [28][160/200]	Time 0.394 (0.440)	Data 0.001 (0.056)	Loss 1.939 (1.184)
Epoch: [28][180/200]	Time 0.381 (0.433)	Data 0.000 (0.050)	Loss 1.401 (1.206)
Epoch: [28][200/200]	Time 0.389 (0.437)	Data 0.001 (0.053)	Loss 1.274 (1.227)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.212)	Data 0.000 (0.082)	
Extract Features: [100/128]	Time 0.127 (0.194)	Data 0.000 (0.064)	
Computing jaccard distance...
Jaccard distance computing time cost: 57.96461796760559
==> Statistics for epoch 29: 1018 clusters
Epoch: [29][20/200]	Time 0.379 (0.434)	Data 0.001 (0.052)	Loss 0.233 (0.254)
Epoch: [29][40/200]	Time 0.385 (0.447)	Data 0.001 (0.065)	Loss 0.778 (0.456)
Epoch: [29][60/200]	Time 0.382 (0.426)	Data 0.000 (0.044)	Loss 1.213 (0.755)
Epoch: [29][80/200]	Time 0.383 (0.434)	Data 0.001 (0.052)	Loss 1.090 (0.918)
Epoch: [29][100/200]	Time 0.380 (0.441)	Data 0.000 (0.058)	Loss 1.151 (1.006)
Epoch: [29][120/200]	Time 0.375 (0.431)	Data 0.000 (0.049)	Loss 1.470 (1.070)
Epoch: [29][140/200]	Time 0.391 (0.437)	Data 0.000 (0.054)	Loss 1.131 (1.113)
Epoch: [29][160/200]	Time 0.391 (0.440)	Data 0.001 (0.057)	Loss 2.055 (1.151)
Epoch: [29][180/200]	Time 0.384 (0.434)	Data 0.000 (0.051)	Loss 1.478 (1.175)
Epoch: [29][200/200]	Time 0.381 (0.437)	Data 0.001 (0.054)	Loss 1.093 (1.195)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.130 (0.205)	Data 0.000 (0.076)	
Extract Features: [100/128]	Time 0.129 (0.188)	Data 0.000 (0.059)	
Computing jaccard distance...
Jaccard distance computing time cost: 57.97105574607849
==> Statistics for epoch 30: 1015 clusters
Epoch: [30][20/200]	Time 0.385 (0.433)	Data 0.001 (0.053)	Loss 0.234 (0.251)
Epoch: [30][40/200]	Time 0.385 (0.446)	Data 0.001 (0.066)	Loss 1.077 (0.484)
Epoch: [30][60/200]	Time 0.384 (0.427)	Data 0.000 (0.044)	Loss 1.332 (0.795)
Epoch: [30][80/200]	Time 0.384 (0.436)	Data 0.001 (0.053)	Loss 1.323 (0.944)
Epoch: [30][100/200]	Time 0.380 (0.441)	Data 0.000 (0.058)	Loss 1.425 (1.040)
Epoch: [30][120/200]	Time 0.384 (0.431)	Data 0.000 (0.048)	Loss 1.636 (1.111)
Epoch: [30][140/200]	Time 0.384 (0.435)	Data 0.000 (0.052)	Loss 1.591 (1.148)
Epoch: [30][160/200]	Time 0.385 (0.439)	Data 0.000 (0.056)	Loss 1.512 (1.173)
Epoch: [30][180/200]	Time 0.383 (0.433)	Data 0.000 (0.050)	Loss 1.603 (1.206)
Epoch: [30][200/200]	Time 0.381 (0.436)	Data 0.000 (0.052)	Loss 1.590 (1.222)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.133 (0.217)	Data 0.000 (0.087)	
Extract Features: [100/128]	Time 0.128 (0.195)	Data 0.000 (0.066)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.293930768966675
==> Statistics for epoch 31: 1016 clusters
Epoch: [31][20/200]	Time 0.377 (0.442)	Data 0.000 (0.055)	Loss 0.255 (0.253)
Epoch: [31][40/200]	Time 0.380 (0.451)	Data 0.001 (0.068)	Loss 1.482 (0.457)
Epoch: [31][60/200]	Time 0.374 (0.428)	Data 0.000 (0.045)	Loss 1.595 (0.765)
Epoch: [31][80/200]	Time 0.381 (0.436)	Data 0.000 (0.054)	Loss 1.120 (0.903)
Epoch: [31][100/200]	Time 0.381 (0.441)	Data 0.000 (0.058)	Loss 1.039 (0.979)
Epoch: [31][120/200]	Time 0.372 (0.431)	Data 0.000 (0.048)	Loss 1.247 (1.048)
Epoch: [31][140/200]	Time 0.382 (0.436)	Data 0.000 (0.053)	Loss 1.179 (1.088)
Epoch: [31][160/200]	Time 0.397 (0.440)	Data 0.002 (0.056)	Loss 1.930 (1.127)
Epoch: [31][180/200]	Time 0.387 (0.434)	Data 0.000 (0.050)	Loss 0.940 (1.158)
Epoch: [31][200/200]	Time 0.384 (0.437)	Data 0.000 (0.053)	Loss 1.281 (1.180)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.126 (0.205)	Data 0.000 (0.077)	
Extract Features: [100/128]	Time 0.126 (0.188)	Data 0.000 (0.059)	
Computing jaccard distance...
Jaccard distance computing time cost: 57.73427653312683
==> Statistics for epoch 32: 1007 clusters
Epoch: [32][20/200]	Time 0.383 (0.441)	Data 0.001 (0.053)	Loss 0.216 (0.276)
Epoch: [32][40/200]	Time 0.381 (0.448)	Data 0.001 (0.063)	Loss 0.984 (0.492)
Epoch: [32][60/200]	Time 0.380 (0.427)	Data 0.000 (0.042)	Loss 1.393 (0.789)
Epoch: [32][80/200]	Time 0.381 (0.435)	Data 0.001 (0.051)	Loss 1.165 (0.918)
Epoch: [32][100/200]	Time 0.379 (0.439)	Data 0.001 (0.055)	Loss 1.293 (1.004)
Epoch: [32][120/200]	Time 0.378 (0.430)	Data 0.000 (0.046)	Loss 1.183 (1.070)
Epoch: [32][140/200]	Time 0.383 (0.435)	Data 0.000 (0.051)	Loss 1.074 (1.125)
Epoch: [32][160/200]	Time 0.383 (0.438)	Data 0.001 (0.054)	Loss 0.957 (1.155)
Epoch: [32][180/200]	Time 0.380 (0.432)	Data 0.000 (0.048)	Loss 1.606 (1.188)
Epoch: [32][200/200]	Time 0.377 (0.434)	Data 0.001 (0.051)	Loss 1.032 (1.199)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.214)	Data 0.000 (0.084)	
Extract Features: [100/128]	Time 0.354 (0.194)	Data 0.227 (0.065)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.7261528968811
==> Statistics for epoch 33: 1018 clusters
Epoch: [33][20/200]	Time 0.380 (0.435)	Data 0.001 (0.053)	Loss 0.225 (0.264)
Epoch: [33][40/200]	Time 0.381 (0.449)	Data 0.001 (0.067)	Loss 1.517 (0.474)
Epoch: [33][60/200]	Time 0.385 (0.427)	Data 0.000 (0.045)	Loss 0.968 (0.763)
Epoch: [33][80/200]	Time 0.383 (0.435)	Data 0.001 (0.053)	Loss 1.164 (0.926)
Epoch: [33][100/200]	Time 0.387 (0.441)	Data 0.001 (0.058)	Loss 1.008 (1.013)
Epoch: [33][120/200]	Time 0.376 (0.431)	Data 0.000 (0.049)	Loss 1.333 (1.063)
Epoch: [33][140/200]	Time 0.386 (0.437)	Data 0.001 (0.053)	Loss 1.255 (1.111)
Epoch: [33][160/200]	Time 0.385 (0.440)	Data 0.001 (0.056)	Loss 1.390 (1.141)
Epoch: [33][180/200]	Time 0.381 (0.434)	Data 0.000 (0.050)	Loss 1.130 (1.164)
Epoch: [33][200/200]	Time 0.402 (0.437)	Data 0.017 (0.053)	Loss 1.805 (1.192)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.129 (0.212)	Data 0.000 (0.082)	
Extract Features: [100/128]	Time 0.128 (0.193)	Data 0.000 (0.062)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.37912392616272
==> Statistics for epoch 34: 1012 clusters
Epoch: [34][20/200]	Time 0.375 (0.433)	Data 0.001 (0.054)	Loss 0.120 (0.268)
Epoch: [34][40/200]	Time 0.390 (0.448)	Data 0.001 (0.068)	Loss 1.294 (0.486)
Epoch: [34][60/200]	Time 0.389 (0.426)	Data 0.000 (0.045)	Loss 1.129 (0.786)
Epoch: [34][80/200]	Time 0.383 (0.437)	Data 0.000 (0.054)	Loss 1.426 (0.934)
Epoch: [34][100/200]	Time 0.384 (0.443)	Data 0.000 (0.060)	Loss 1.338 (1.019)
Epoch: [34][120/200]	Time 0.382 (0.433)	Data 0.000 (0.050)	Loss 1.725 (1.079)
Epoch: [34][140/200]	Time 0.385 (0.437)	Data 0.000 (0.054)	Loss 1.272 (1.131)
Epoch: [34][160/200]	Time 0.390 (0.441)	Data 0.001 (0.057)	Loss 1.480 (1.157)
Epoch: [34][180/200]	Time 0.391 (0.435)	Data 0.000 (0.051)	Loss 1.481 (1.183)
Epoch: [34][200/200]	Time 0.384 (0.438)	Data 0.001 (0.053)	Loss 1.317 (1.194)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.218)	Data 0.000 (0.088)	
Extract Features: [100/128]	Time 0.128 (0.197)	Data 0.000 (0.067)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.95721101760864
==> Statistics for epoch 35: 1017 clusters
Epoch: [35][20/200]	Time 0.379 (0.437)	Data 0.001 (0.056)	Loss 0.250 (0.233)
Epoch: [35][40/200]	Time 0.382 (0.449)	Data 0.001 (0.069)	Loss 1.401 (0.462)
Epoch: [35][60/200]	Time 0.383 (0.426)	Data 0.000 (0.046)	Loss 1.209 (0.758)
Epoch: [35][80/200]	Time 0.382 (0.435)	Data 0.001 (0.053)	Loss 1.681 (0.913)
Epoch: [35][100/200]	Time 0.382 (0.440)	Data 0.001 (0.058)	Loss 1.472 (1.029)
Epoch: [35][120/200]	Time 0.378 (0.431)	Data 0.000 (0.048)	Loss 1.261 (1.088)
Epoch: [35][140/200]	Time 0.384 (0.434)	Data 0.001 (0.052)	Loss 1.511 (1.124)
Epoch: [35][160/200]	Time 0.385 (0.438)	Data 0.000 (0.055)	Loss 1.608 (1.154)
Epoch: [35][180/200]	Time 0.379 (0.432)	Data 0.000 (0.049)	Loss 1.153 (1.180)
Epoch: [35][200/200]	Time 0.388 (0.435)	Data 0.000 (0.052)	Loss 0.940 (1.198)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.126 (0.206)	Data 0.000 (0.075)	
Extract Features: [100/128]	Time 0.130 (0.191)	Data 0.000 (0.062)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.31871199607849
==> Statistics for epoch 36: 1015 clusters
Epoch: [36][20/200]	Time 0.377 (0.437)	Data 0.001 (0.054)	Loss 0.190 (0.251)
Epoch: [36][40/200]	Time 0.383 (0.446)	Data 0.001 (0.065)	Loss 1.171 (0.484)
Epoch: [36][60/200]	Time 0.381 (0.425)	Data 0.000 (0.043)	Loss 1.284 (0.755)
Epoch: [36][80/200]	Time 0.385 (0.435)	Data 0.001 (0.052)	Loss 1.707 (0.907)
Epoch: [36][100/200]	Time 0.375 (0.440)	Data 0.001 (0.057)	Loss 1.189 (0.996)
Epoch: [36][120/200]	Time 0.373 (0.430)	Data 0.000 (0.048)	Loss 1.084 (1.076)
Epoch: [36][140/200]	Time 0.386 (0.436)	Data 0.001 (0.052)	Loss 1.540 (1.121)
Epoch: [36][160/200]	Time 0.386 (0.439)	Data 0.001 (0.056)	Loss 1.373 (1.159)
Epoch: [36][180/200]	Time 0.380 (0.433)	Data 0.000 (0.050)	Loss 1.212 (1.183)
Epoch: [36][200/200]	Time 0.389 (0.437)	Data 0.001 (0.053)	Loss 1.146 (1.210)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.210)	Data 0.000 (0.078)	
Extract Features: [100/128]	Time 0.196 (0.192)	Data 0.071 (0.062)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.701112270355225
==> Statistics for epoch 37: 1017 clusters
Epoch: [37][20/200]	Time 0.376 (0.441)	Data 0.001 (0.058)	Loss 0.124 (0.246)
Epoch: [37][40/200]	Time 0.386 (0.453)	Data 0.001 (0.070)	Loss 1.149 (0.484)
Epoch: [37][60/200]	Time 0.382 (0.430)	Data 0.000 (0.047)	Loss 1.506 (0.789)
Epoch: [37][80/200]	Time 0.384 (0.441)	Data 0.002 (0.057)	Loss 1.431 (0.935)
Epoch: [37][100/200]	Time 0.387 (0.447)	Data 0.001 (0.062)	Loss 0.945 (1.013)
Epoch: [37][120/200]	Time 0.380 (0.437)	Data 0.000 (0.052)	Loss 1.288 (1.085)
Epoch: [37][140/200]	Time 0.386 (0.441)	Data 0.001 (0.057)	Loss 1.120 (1.108)
Epoch: [37][160/200]	Time 0.384 (0.444)	Data 0.001 (0.059)	Loss 1.732 (1.150)
Epoch: [37][180/200]	Time 0.382 (0.438)	Data 0.000 (0.053)	Loss 1.672 (1.181)
Epoch: [37][200/200]	Time 0.384 (0.441)	Data 0.001 (0.056)	Loss 1.509 (1.199)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.127 (0.207)	Data 0.000 (0.075)	
Extract Features: [100/128]	Time 0.127 (0.192)	Data 0.000 (0.061)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.56865739822388
==> Statistics for epoch 38: 1025 clusters
Epoch: [38][20/200]	Time 0.375 (0.434)	Data 0.001 (0.054)	Loss 0.311 (0.245)
Epoch: [38][40/200]	Time 0.385 (0.448)	Data 0.002 (0.066)	Loss 1.434 (0.451)
Epoch: [38][60/200]	Time 0.376 (0.427)	Data 0.000 (0.044)	Loss 1.127 (0.746)
Epoch: [38][80/200]	Time 0.385 (0.438)	Data 0.001 (0.055)	Loss 1.570 (0.908)
Epoch: [38][100/200]	Time 0.387 (0.444)	Data 0.001 (0.061)	Loss 1.524 (1.003)
Epoch: [38][120/200]	Time 0.379 (0.434)	Data 0.001 (0.051)	Loss 0.913 (1.067)
Epoch: [38][140/200]	Time 0.384 (0.439)	Data 0.001 (0.055)	Loss 1.684 (1.125)
Epoch: [38][160/200]	Time 0.384 (0.432)	Data 0.000 (0.048)	Loss 1.312 (1.154)
Epoch: [38][180/200]	Time 0.383 (0.437)	Data 0.000 (0.052)	Loss 1.727 (1.174)
Epoch: [38][200/200]	Time 0.387 (0.440)	Data 0.000 (0.055)	Loss 1.468 (1.193)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.127 (0.212)	Data 0.000 (0.081)	
Extract Features: [100/128]	Time 0.130 (0.193)	Data 0.000 (0.063)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.78541541099548
==> Statistics for epoch 39: 1023 clusters
Epoch: [39][20/200]	Time 0.380 (0.436)	Data 0.001 (0.055)	Loss 0.414 (0.272)
Epoch: [39][40/200]	Time 0.382 (0.446)	Data 0.001 (0.065)	Loss 1.163 (0.476)
Epoch: [39][60/200]	Time 0.377 (0.424)	Data 0.000 (0.044)	Loss 1.518 (0.778)
Epoch: [39][80/200]	Time 0.388 (0.434)	Data 0.001 (0.053)	Loss 1.490 (0.950)
Epoch: [39][100/200]	Time 0.382 (0.440)	Data 0.001 (0.059)	Loss 1.746 (1.040)
Epoch: [39][120/200]	Time 0.382 (0.431)	Data 0.000 (0.049)	Loss 1.633 (1.087)
Epoch: [39][140/200]	Time 0.385 (0.436)	Data 0.001 (0.053)	Loss 1.874 (1.143)
Epoch: [39][160/200]	Time 0.385 (0.439)	Data 0.000 (0.056)	Loss 1.317 (1.171)
Epoch: [39][180/200]	Time 0.379 (0.433)	Data 0.000 (0.049)	Loss 1.559 (1.195)
Epoch: [39][200/200]	Time 0.379 (0.436)	Data 0.001 (0.052)	Loss 1.365 (1.217)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.136 (0.213)	Data 0.007 (0.083)	
Extract Features: [100/128]	Time 0.128 (0.195)	Data 0.000 (0.066)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.70965027809143
==> Statistics for epoch 40: 1011 clusters
Epoch: [40][20/200]	Time 0.377 (0.428)	Data 0.001 (0.047)	Loss 0.210 (0.263)
Epoch: [40][40/200]	Time 0.382 (0.444)	Data 0.001 (0.064)	Loss 1.655 (0.480)
Epoch: [40][60/200]	Time 0.377 (0.424)	Data 0.000 (0.043)	Loss 1.462 (0.769)
Epoch: [40][80/200]	Time 0.387 (0.435)	Data 0.001 (0.052)	Loss 1.395 (0.891)
Epoch: [40][100/200]	Time 0.375 (0.440)	Data 0.000 (0.058)	Loss 1.361 (1.005)
Epoch: [40][120/200]	Time 0.380 (0.431)	Data 0.000 (0.048)	Loss 1.222 (1.077)
Epoch: [40][140/200]	Time 0.386 (0.435)	Data 0.000 (0.052)	Loss 1.330 (1.121)
Epoch: [40][160/200]	Time 0.385 (0.438)	Data 0.001 (0.055)	Loss 1.205 (1.169)
Epoch: [40][180/200]	Time 0.380 (0.432)	Data 0.000 (0.049)	Loss 1.343 (1.195)
Epoch: [40][200/200]	Time 0.374 (0.435)	Data 0.000 (0.052)	Loss 1.397 (1.219)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.126 (0.208)	Data 0.000 (0.078)	
Extract Features: [100/128]	Time 0.127 (0.192)	Data 0.000 (0.062)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.610878705978394
==> Statistics for epoch 41: 1015 clusters
Epoch: [41][20/200]	Time 0.380 (0.437)	Data 0.001 (0.055)	Loss 0.183 (0.240)
Epoch: [41][40/200]	Time 0.384 (0.450)	Data 0.001 (0.068)	Loss 1.243 (0.542)
Epoch: [41][60/200]	Time 0.382 (0.427)	Data 0.000 (0.046)	Loss 1.179 (0.811)
Epoch: [41][80/200]	Time 0.386 (0.437)	Data 0.001 (0.055)	Loss 1.245 (0.934)
Epoch: [41][100/200]	Time 0.387 (0.443)	Data 0.001 (0.060)	Loss 2.025 (1.017)
Epoch: [41][120/200]	Time 0.382 (0.433)	Data 0.000 (0.050)	Loss 1.310 (1.080)
Epoch: [41][140/200]	Time 0.385 (0.438)	Data 0.001 (0.054)	Loss 1.293 (1.115)
Epoch: [41][160/200]	Time 0.390 (0.441)	Data 0.001 (0.057)	Loss 1.573 (1.147)
Epoch: [41][180/200]	Time 0.384 (0.435)	Data 0.000 (0.051)	Loss 1.117 (1.166)
Epoch: [41][200/200]	Time 0.385 (0.438)	Data 0.001 (0.054)	Loss 1.100 (1.188)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.210)	Data 0.000 (0.083)	
Extract Features: [100/128]	Time 0.127 (0.190)	Data 0.000 (0.062)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.264435052871704
==> Statistics for epoch 42: 1024 clusters
Epoch: [42][20/200]	Time 0.376 (0.436)	Data 0.001 (0.055)	Loss 0.254 (0.232)
Epoch: [42][40/200]	Time 0.383 (0.451)	Data 0.001 (0.070)	Loss 1.406 (0.462)
Epoch: [42][60/200]	Time 0.383 (0.429)	Data 0.000 (0.047)	Loss 1.640 (0.750)
Epoch: [42][80/200]	Time 0.386 (0.440)	Data 0.001 (0.055)	Loss 1.145 (0.908)
Epoch: [42][100/200]	Time 0.386 (0.446)	Data 0.000 (0.061)	Loss 2.145 (0.991)
Epoch: [42][120/200]	Time 0.379 (0.436)	Data 0.000 (0.051)	Loss 1.695 (1.046)
Epoch: [42][140/200]	Time 0.381 (0.441)	Data 0.001 (0.055)	Loss 0.993 (1.101)
Epoch: [42][160/200]	Time 0.386 (0.434)	Data 0.000 (0.048)	Loss 1.682 (1.136)
Epoch: [42][180/200]	Time 0.389 (0.437)	Data 0.004 (0.052)	Loss 1.181 (1.178)
Epoch: [42][200/200]	Time 0.385 (0.440)	Data 0.001 (0.055)	Loss 1.336 (1.200)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.127 (0.216)	Data 0.000 (0.084)	
Extract Features: [100/128]	Time 0.128 (0.194)	Data 0.000 (0.063)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.69758677482605
==> Statistics for epoch 43: 1020 clusters
Epoch: [43][20/200]	Time 0.375 (0.436)	Data 0.001 (0.054)	Loss 0.356 (0.264)
Epoch: [43][40/200]	Time 0.384 (0.448)	Data 0.001 (0.067)	Loss 1.107 (0.509)
Epoch: [43][60/200]	Time 0.384 (0.426)	Data 0.000 (0.045)	Loss 1.024 (0.768)
Epoch: [43][80/200]	Time 0.381 (0.435)	Data 0.001 (0.053)	Loss 1.405 (0.936)
Epoch: [43][100/200]	Time 0.382 (0.441)	Data 0.001 (0.058)	Loss 1.251 (1.027)
Epoch: [43][120/200]	Time 0.384 (0.432)	Data 0.000 (0.049)	Loss 1.721 (1.083)
Epoch: [43][140/200]	Time 0.384 (0.436)	Data 0.001 (0.053)	Loss 1.053 (1.131)
Epoch: [43][160/200]	Time 0.388 (0.439)	Data 0.001 (0.055)	Loss 1.180 (1.164)
Epoch: [43][180/200]	Time 0.390 (0.433)	Data 0.000 (0.049)	Loss 1.447 (1.185)
Epoch: [43][200/200]	Time 0.384 (0.436)	Data 0.001 (0.052)	Loss 1.257 (1.202)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.492 (0.213)	Data 0.366 (0.082)	
Extract Features: [100/128]	Time 0.128 (0.193)	Data 0.000 (0.062)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.69449043273926
==> Statistics for epoch 44: 1024 clusters
Epoch: [44][20/200]	Time 0.387 (0.437)	Data 0.001 (0.055)	Loss 0.242 (0.244)
Epoch: [44][40/200]	Time 0.386 (0.449)	Data 0.001 (0.065)	Loss 0.972 (0.444)
Epoch: [44][60/200]	Time 0.382 (0.428)	Data 0.000 (0.043)	Loss 1.534 (0.759)
Epoch: [44][80/200]	Time 0.384 (0.437)	Data 0.001 (0.053)	Loss 1.120 (0.891)
Epoch: [44][100/200]	Time 0.382 (0.443)	Data 0.001 (0.060)	Loss 1.524 (0.987)
Epoch: [44][120/200]	Time 0.381 (0.433)	Data 0.001 (0.050)	Loss 1.441 (1.056)
Epoch: [44][140/200]	Time 0.383 (0.437)	Data 0.001 (0.053)	Loss 1.749 (1.103)
Epoch: [44][160/200]	Time 0.375 (0.430)	Data 0.000 (0.047)	Loss 1.272 (1.136)
Epoch: [44][180/200]	Time 0.381 (0.433)	Data 0.001 (0.050)	Loss 1.204 (1.159)
Epoch: [44][200/200]	Time 0.387 (0.436)	Data 0.001 (0.053)	Loss 1.124 (1.174)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.126 (0.211)	Data 0.000 (0.081)	
Extract Features: [100/128]	Time 0.128 (0.192)	Data 0.000 (0.062)	
Computing jaccard distance...
Jaccard distance computing time cost: 57.969310998916626
==> Statistics for epoch 45: 1028 clusters
Epoch: [45][20/200]	Time 0.382 (0.431)	Data 0.001 (0.051)	Loss 0.197 (0.259)
Epoch: [45][40/200]	Time 0.384 (0.442)	Data 0.001 (0.063)	Loss 1.231 (0.484)
Epoch: [45][60/200]	Time 0.375 (0.424)	Data 0.000 (0.042)	Loss 1.148 (0.766)
Epoch: [45][80/200]	Time 0.388 (0.433)	Data 0.000 (0.050)	Loss 1.400 (0.920)
Epoch: [45][100/200]	Time 0.382 (0.438)	Data 0.001 (0.055)	Loss 1.434 (1.015)
Epoch: [45][120/200]	Time 0.387 (0.430)	Data 0.001 (0.046)	Loss 1.215 (1.073)
Epoch: [45][140/200]	Time 0.385 (0.434)	Data 0.000 (0.050)	Loss 1.308 (1.122)
Epoch: [45][160/200]	Time 0.383 (0.427)	Data 0.000 (0.044)	Loss 1.807 (1.151)
Epoch: [45][180/200]	Time 0.382 (0.431)	Data 0.000 (0.048)	Loss 0.982 (1.180)
Epoch: [45][200/200]	Time 0.382 (0.435)	Data 0.000 (0.051)	Loss 1.208 (1.201)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.210)	Data 0.000 (0.080)	
Extract Features: [100/128]	Time 0.129 (0.191)	Data 0.000 (0.062)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.10951042175293
==> Statistics for epoch 46: 1031 clusters
Epoch: [46][20/200]	Time 0.384 (0.433)	Data 0.001 (0.051)	Loss 0.161 (0.255)
Epoch: [46][40/200]	Time 0.396 (0.446)	Data 0.001 (0.064)	Loss 1.726 (0.451)
Epoch: [46][60/200]	Time 0.384 (0.425)	Data 0.000 (0.043)	Loss 1.632 (0.762)
Epoch: [46][80/200]	Time 0.380 (0.434)	Data 0.001 (0.052)	Loss 1.115 (0.914)
Epoch: [46][100/200]	Time 0.378 (0.440)	Data 0.001 (0.058)	Loss 1.609 (0.999)
Epoch: [46][120/200]	Time 0.389 (0.433)	Data 0.001 (0.048)	Loss 1.067 (1.054)
Epoch: [46][140/200]	Time 0.386 (0.438)	Data 0.001 (0.053)	Loss 1.268 (1.091)
Epoch: [46][160/200]	Time 0.382 (0.431)	Data 0.000 (0.047)	Loss 1.420 (1.130)
Epoch: [46][180/200]	Time 0.391 (0.435)	Data 0.001 (0.050)	Loss 1.085 (1.167)
Epoch: [46][200/200]	Time 0.388 (0.438)	Data 0.001 (0.053)	Loss 1.405 (1.181)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.215)	Data 0.000 (0.087)	
Extract Features: [100/128]	Time 0.128 (0.195)	Data 0.000 (0.066)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.19704079627991
==> Statistics for epoch 47: 1019 clusters
Epoch: [47][20/200]	Time 0.380 (0.439)	Data 0.000 (0.053)	Loss 0.199 (0.248)
Epoch: [47][40/200]	Time 0.381 (0.453)	Data 0.002 (0.070)	Loss 1.279 (0.470)
Epoch: [47][60/200]	Time 0.376 (0.429)	Data 0.000 (0.047)	Loss 1.177 (0.769)
Epoch: [47][80/200]	Time 0.385 (0.438)	Data 0.001 (0.055)	Loss 1.389 (0.909)
Epoch: [47][100/200]	Time 0.379 (0.443)	Data 0.000 (0.060)	Loss 1.150 (1.000)
Epoch: [47][120/200]	Time 0.378 (0.433)	Data 0.000 (0.051)	Loss 1.100 (1.057)
Epoch: [47][140/200]	Time 0.378 (0.438)	Data 0.000 (0.055)	Loss 1.430 (1.103)
Epoch: [47][160/200]	Time 0.381 (0.441)	Data 0.001 (0.058)	Loss 1.324 (1.136)
Epoch: [47][180/200]	Time 0.381 (0.434)	Data 0.000 (0.052)	Loss 1.097 (1.161)
Epoch: [47][200/200]	Time 0.382 (0.436)	Data 0.000 (0.054)	Loss 1.606 (1.177)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.125 (0.213)	Data 0.000 (0.083)	
Extract Features: [100/128]	Time 0.128 (0.197)	Data 0.000 (0.068)	
Computing jaccard distance...
Jaccard distance computing time cost: 57.97888231277466
==> Statistics for epoch 48: 1020 clusters
Epoch: [48][20/200]	Time 0.383 (0.436)	Data 0.001 (0.054)	Loss 0.219 (0.243)
Epoch: [48][40/200]	Time 0.384 (0.450)	Data 0.001 (0.065)	Loss 1.476 (0.488)
Epoch: [48][60/200]	Time 0.381 (0.427)	Data 0.000 (0.043)	Loss 1.293 (0.765)
Epoch: [48][80/200]	Time 0.384 (0.436)	Data 0.001 (0.052)	Loss 1.437 (0.914)
Epoch: [48][100/200]	Time 0.381 (0.440)	Data 0.001 (0.056)	Loss 1.849 (1.007)
Epoch: [48][120/200]	Time 0.381 (0.430)	Data 0.000 (0.047)	Loss 1.052 (1.076)
Epoch: [48][140/200]	Time 0.389 (0.435)	Data 0.001 (0.052)	Loss 1.360 (1.113)
Epoch: [48][160/200]	Time 0.385 (0.438)	Data 0.001 (0.055)	Loss 1.131 (1.153)
Epoch: [48][180/200]	Time 0.386 (0.432)	Data 0.000 (0.049)	Loss 1.444 (1.170)
Epoch: [48][200/200]	Time 0.384 (0.434)	Data 0.001 (0.051)	Loss 1.333 (1.192)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.128 (0.216)	Data 0.000 (0.086)	
Extract Features: [100/128]	Time 0.175 (0.194)	Data 0.049 (0.064)	
Computing jaccard distance...
Jaccard distance computing time cost: 57.996073484420776
==> Statistics for epoch 49: 1019 clusters
Epoch: [49][20/200]	Time 0.378 (0.434)	Data 0.001 (0.052)	Loss 0.247 (0.238)
Epoch: [49][40/200]	Time 0.384 (0.445)	Data 0.001 (0.062)	Loss 1.401 (0.481)
Epoch: [49][60/200]	Time 0.379 (0.426)	Data 0.000 (0.042)	Loss 1.251 (0.746)
Epoch: [49][80/200]	Time 0.386 (0.434)	Data 0.001 (0.050)	Loss 1.456 (0.887)
Epoch: [49][100/200]	Time 0.382 (0.440)	Data 0.001 (0.056)	Loss 1.228 (0.978)
Epoch: [49][120/200]	Time 0.385 (0.430)	Data 0.000 (0.047)	Loss 1.589 (1.047)
Epoch: [49][140/200]	Time 0.385 (0.435)	Data 0.001 (0.052)	Loss 1.623 (1.106)
Epoch: [49][160/200]	Time 0.386 (0.439)	Data 0.001 (0.055)	Loss 1.081 (1.128)
Epoch: [49][180/200]	Time 0.385 (0.433)	Data 0.000 (0.049)	Loss 1.337 (1.166)
Epoch: [49][200/200]	Time 0.384 (0.435)	Data 0.000 (0.052)	Loss 1.366 (1.183)
Extract Features: [50/367]	Time 0.132 (0.220)	Data 0.000 (0.089)	
Extract Features: [100/367]	Time 0.129 (0.200)	Data 0.000 (0.069)	
Extract Features: [150/367]	Time 0.128 (0.195)	Data 0.000 (0.066)	
Extract Features: [200/367]	Time 0.128 (0.190)	Data 0.000 (0.061)	
Extract Features: [250/367]	Time 0.160 (0.188)	Data 0.027 (0.058)	
Extract Features: [300/367]	Time 0.126 (0.186)	Data 0.000 (0.056)	
Extract Features: [350/367]	Time 0.225 (0.185)	Data 0.097 (0.055)	
Mean AP: 55.0%

 * Finished epoch  49  model mAP: 55.0%  best: 55.0% *

==> Test with the best model:
=> Loaded checkpoint 'log/msmt17/vit_small_cion/model_best.pth.tar'
Extract Features: [50/367]	Time 0.125 (0.209)	Data 0.001 (0.082)	
Extract Features: [100/367]	Time 0.303 (0.198)	Data 0.182 (0.072)	
Extract Features: [150/367]	Time 0.126 (0.192)	Data 0.001 (0.065)	
Extract Features: [200/367]	Time 0.125 (0.191)	Data 0.000 (0.064)	
Extract Features: [250/367]	Time 0.290 (0.190)	Data 0.000 (0.062)	
Extract Features: [300/367]	Time 0.126 (0.189)	Data 0.000 (0.062)	
Extract Features: [350/367]	Time 0.134 (0.187)	Data 0.000 (0.060)	
Mean AP: 55.0%
CMC Scores:
  top-1          78.4%
  top-5          87.2%
  top-10         89.7%
Total running time:  2:41:32.052869
