running w CUDA 11.1 

(proxy) [jalal@goku proxynca_pp]$ pwd

/scratch3/research/code/fashion/proxynca_pp

(proxy) [jalal@goku proxynca_pp]$ CUDA_VISIBLE_DEVICES=0,1 python train.py --dataset cub  --config config/cub.json --mode train --apex --seed 0 --workers 12
(1024, 4096)
train.py:12: MatplotlibDeprecationWarning: The 'warn' parameter of use() is deprecated since Matplotlib 3.1 and will be removed in 3.3.  If any parameter follows 'warn', they should be pass as keyword, not positionally.
  matplotlib.use('agg', warn=False, force=True)
/scratch3/venv/proxy/lib/python3.8/site-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at  /pytorch/c10/core/TensorImpl.h:1156.)
  return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
best_epoch 40
===
Selected optimization level O1:  Insert automatic casts around Pytorch functions and Tensor methods.

Defaults for this optimization level are:
enabled                : True
opt_level              : O1
cast_model_type        : None
patch_torch_functions  : True
keep_batchnorm_fp32    : None
master_weights         : None
loss_scale             : dynamic
Processing user overrides (additional kwargs that are not None)...
After processing overrides, optimization options are:
enabled                : True
opt_level              : O1
cast_model_type        : None
patch_torch_functions  : True
keep_batchnorm_fp32    : None
master_weights         : None
loss_scale             : dynamic
2021-09-14 15:31:29,186 Training parameters: {'dataset': 'cub', 'config': 'config/cub.json', 'sz_embedding': 2048, 'sz_batch': 32, 'nb_epochs': 40, 'log_filename': 'cub_cub_train_0', 'nb_workers': 12, 'seed': 0, 'mode': 'train', 'lr_steps': [1000], 'source_dir': '', 'root_dir': '', 'eval_nmi': False, 'recall': [1, 2, 4, 8], 'init_eval': False, 'no_warmup': False, 'apex': True, 'warmup_k': 5}
2021-09-14 15:31:29,186 Training for 40 epochs.
90
2021-09-14 15:31:29,186 **warm up for 5 epochs.**
2021-09-14 15:31:49,340 warm up ends in 5 epochs
2021-09-14 15:32:07,282 warm up ends in 4 epochs
2021-09-14 15:32:25,363 warm up ends in 3 epochs
2021-09-14 15:32:43,324 warm up ends in 2 epochs
2021-09-14 15:33:01,336 warm up ends in 1 epochs
0.004 0.004
it: 90
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 400.0
    weight_decay: 0
)
2021-09-14 15:33:19,358 Epoch: 0, loss: 1.320, time (seconds): 18.02.
2021-09-14 15:33:19,359 **Validation...**
done collecting prediction
2021-09-14 15:33:26,697 NMI: 100.000
2021-09-14 15:33:27,593 R@1 : 78.387
2021-09-14 15:33:27,632 R@2 : 85.210
2021-09-14 15:33:27,708 R@4 : 91.092
2021-09-14 15:33:27,748 R@8 : 95.697
2021-09-14 15:33:27,748 hmean: 0.8788392688901451
2021-09-14 15:33:27,748 Eval time: 8.39
2021-09-14 15:33:27,749 Best val epoch: 0
2021-09-14 15:33:27,749 Best val hmean: 0.8788392688901451
2021-09-14 15:33:27,749 Best val nmi: 1
2021-09-14 15:33:27,749 Best val r1: 0.7838655462184874
2021-09-14 15:33:27,749 []
0.004 0.004
it: 180
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 400.0
    weight_decay: 0
)
2021-09-14 15:33:45,796 Epoch: 1, loss: 1.307, time (seconds): 18.05.
2021-09-14 15:33:45,797 **Validation...**
done collecting prediction
2021-09-14 15:33:53,058 NMI: 100.000
2021-09-14 15:33:53,935 R@1 : 79.227
2021-09-14 15:33:53,976 R@2 : 86.454
2021-09-14 15:33:54,054 R@4 : 91.832
2021-09-14 15:33:54,095 R@8 : 96.370
2021-09-14 15:33:54,095 hmean: 0.8840960240060016
2021-09-14 15:33:54,095 Eval time: 8.30
2021-09-14 15:33:54,096 Best val epoch: 1
2021-09-14 15:33:54,096 Best val hmean: 0.8840960240060016
2021-09-14 15:33:54,096 Best val nmi: 1
2021-09-14 15:33:54,097 Best val r1: 0.7922689075630253
2021-09-14 15:33:54,097 []
0.004 0.004
it: 270
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 400.0
    weight_decay: 0
)
2021-09-14 15:34:12,151 Epoch: 2, loss: 1.112, time (seconds): 18.05.
2021-09-14 15:34:12,151 **Validation...**
done collecting prediction
2021-09-14 15:34:19,374 NMI: 100.000
2021-09-14 15:34:20,289 R@1 : 79.328
2021-09-14 15:34:20,329 R@2 : 87.328
2021-09-14 15:34:20,370 R@4 : 92.067
2021-09-14 15:34:20,410 R@8 : 95.966
2021-09-14 15:34:20,410 hmean: 0.8847235238987816
2021-09-14 15:34:20,410 Eval time: 8.26
2021-09-14 15:34:20,411 Best val epoch: 2
2021-09-14 15:34:20,411 Best val hmean: 0.8847235238987816
2021-09-14 15:34:20,411 Best val nmi: 1
2021-09-14 15:34:20,411 Best val r1: 0.7932773109243697
2021-09-14 15:34:20,412 []
0.004 0.004
it: 360
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 400.0
    weight_decay: 0
)
2021-09-14 15:34:38,466 Epoch: 3, loss: 1.010, time (seconds): 18.05.
2021-09-14 15:34:38,466 **Validation...**
done collecting prediction
2021-09-14 15:34:45,685 NMI: 100.000
2021-09-14 15:34:46,601 R@1 : 80.908
2021-09-14 15:34:46,642 R@2 : 87.697
2021-09-14 15:34:46,682 R@4 : 92.773
2021-09-14 15:34:46,722 R@8 : 96.235
2021-09-14 15:34:46,722 hmean: 0.8944630248978076
2021-09-14 15:34:46,722 Eval time: 8.26
2021-09-14 15:34:46,723 Best val epoch: 3
2021-09-14 15:34:46,723 Best val hmean: 0.8944630248978076
2021-09-14 15:34:46,723 Best val nmi: 1
2021-09-14 15:34:46,723 Best val r1: 0.8090756302521008
2021-09-14 15:34:46,723 []
0.004 0.004
it: 450
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 400.0
    weight_decay: 0
)
2021-09-14 15:35:04,854 Epoch: 4, loss: 1.021, time (seconds): 18.13.
2021-09-14 15:35:04,854 **Validation...**
done collecting prediction
2021-09-14 15:35:12,026 NMI: 100.000
2021-09-14 15:35:12,951 R@1 : 79.866
2021-09-14 15:35:12,991 R@2 : 86.790
2021-09-14 15:35:13,031 R@4 : 92.773
2021-09-14 15:35:13,070 R@8 : 96.101
2021-09-14 15:35:13,070 hmean: 0.888058306858531
2021-09-14 15:35:13,070 Eval time: 8.22
2021-09-14 15:35:13,070 Best val epoch: 3
2021-09-14 15:35:13,070 Best val hmean: 0.8944630248978076
2021-09-14 15:35:13,070 Best val nmi: 1
2021-09-14 15:35:13,070 Best val r1: 0.8090756302521008
2021-09-14 15:35:13,070 []
0.004 0.004
it: 540
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 400.0
    weight_decay: 0
)
2021-09-14 15:35:31,171 Epoch: 5, loss: 0.936, time (seconds): 18.10.
2021-09-14 15:35:31,172 **Validation...**
done collecting prediction
2021-09-14 15:35:38,402 NMI: 100.000
2021-09-14 15:35:39,297 R@1 : 80.807
2021-09-14 15:35:39,337 R@2 : 87.765
2021-09-14 15:35:39,413 R@4 : 93.042
2021-09-14 15:35:39,453 R@8 : 96.101
2021-09-14 15:35:39,453 hmean: 0.8938464398587098
2021-09-14 15:35:39,453 Eval time: 8.28
2021-09-14 15:35:39,454 Best val epoch: 3
2021-09-14 15:35:39,454 Best val hmean: 0.8944630248978076
2021-09-14 15:35:39,455 Best val nmi: 1
2021-09-14 15:35:39,455 Best val r1: 0.8090756302521008
2021-09-14 15:35:39,455 []
0.004 0.004
it: 630
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 400.0
    weight_decay: 0
)
2021-09-14 15:35:57,610 Epoch: 6, loss: 0.987, time (seconds): 18.15.
2021-09-14 15:35:57,610 **Validation...**
done collecting prediction
2021-09-14 15:36:04,844 NMI: 100.000
2021-09-14 15:36:05,857 R@1 : 80.807
2021-09-14 15:36:05,896 R@2 : 87.697
2021-09-14 15:36:05,935 R@4 : 92.571
2021-09-14 15:36:05,975 R@8 : 96.034
2021-09-14 15:36:05,975 hmean: 0.8938464398587098
2021-09-14 15:36:05,975 Eval time: 8.37
2021-09-14 15:36:05,975 Best val epoch: 3
2021-09-14 15:36:05,975 Best val hmean: 0.8944630248978076
2021-09-14 15:36:05,975 Best val nmi: 1
2021-09-14 15:36:05,975 Best val r1: 0.8090756302521008
2021-09-14 15:36:05,975 []
0.004 0.004
it: 720
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 400.0
    weight_decay: 0
)
2021-09-14 15:36:24,218 Epoch: 7, loss: 0.781, time (seconds): 18.24.
2021-09-14 15:36:24,219 **Validation...**
done collecting prediction
2021-09-14 15:36:31,578 NMI: 100.000
2021-09-14 15:36:32,546 R@1 : 80.874
2021-09-14 15:36:32,586 R@2 : 88.269
2021-09-14 15:36:32,626 R@4 : 92.874
2021-09-14 15:36:32,666 R@8 : 96.303
2021-09-14 15:36:32,666 hmean: 0.8942575729418323
2021-09-14 15:36:32,666 Eval time: 8.45
2021-09-14 15:36:32,666 Best val epoch: 3
2021-09-14 15:36:32,666 Best val hmean: 0.8944630248978076
2021-09-14 15:36:32,666 Best val nmi: 1
2021-09-14 15:36:32,666 Best val r1: 0.8090756302521008
2021-09-14 15:36:32,667 []
0.004 0.004
it: 810
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 400.0
    weight_decay: 0
)
2021-09-14 15:36:51,128 Epoch: 8, loss: 0.868, time (seconds): 18.46.
2021-09-14 15:36:51,128 **Validation...**
done collecting prediction
2021-09-14 15:36:58,477 NMI: 100.000
2021-09-14 15:36:59,487 R@1 : 80.571
2021-09-14 15:36:59,525 R@2 : 87.933
2021-09-14 15:36:59,564 R@4 : 92.739
2021-09-14 15:36:59,603 R@8 : 96.134
2021-09-14 15:36:59,603 hmean: 0.8924050632911393
2021-09-14 15:36:59,603 Eval time: 8.47
2021-09-14 15:36:59,603 Best val epoch: 3
2021-09-14 15:36:59,603 Best val hmean: 0.8944630248978076
2021-09-14 15:36:59,603 Best val nmi: 1
2021-09-14 15:36:59,603 Best val r1: 0.8090756302521008
2021-09-14 15:36:59,603 []
0.004 0.0004
it: 900
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 40.0
    weight_decay: 0
)
2021-09-14 15:37:17,977 Epoch: 9, loss: 0.755, time (seconds): 18.37.
2021-09-14 15:37:17,977 **Validation...**
done collecting prediction
2021-09-14 15:37:25,254 NMI: 100.000
2021-09-14 15:37:26,131 R@1 : 81.378
2021-09-14 15:37:26,169 R@2 : 88.303
2021-09-14 15:37:26,206 R@4 : 93.042
2021-09-14 15:37:26,244 R@8 : 96.303
2021-09-14 15:37:26,244 hmean: 0.8973313565604152
2021-09-14 15:37:26,244 Eval time: 8.27
2021-09-14 15:37:26,245 Best val epoch: 9
2021-09-14 15:37:26,245 Best val hmean: 0.8973313565604152
2021-09-14 15:37:26,245 Best val nmi: 1
2021-09-14 15:37:26,245 Best val r1: 0.8137815126050421
2021-09-14 15:37:26,245 [9]
0.0004 0.0004
it: 990
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 40.0
    weight_decay: 0
)
2021-09-14 15:37:44,627 Epoch: 10, loss: 0.733, time (seconds): 18.38.
2021-09-14 15:37:44,627 **Validation...**
done collecting prediction
2021-09-14 15:37:51,932 NMI: 100.000
2021-09-14 15:37:52,816 R@1 : 80.941
2021-09-14 15:37:52,856 R@2 : 87.966
2021-09-14 15:37:52,933 R@4 : 92.706
2021-09-14 15:37:52,973 R@8 : 96.303
2021-09-14 15:37:52,973 hmean: 0.8946684005201561
2021-09-14 15:37:52,973 Eval time: 8.35
2021-09-14 15:37:52,974 Best val epoch: 9
2021-09-14 15:37:52,974 Best val hmean: 0.8973313565604152
2021-09-14 15:37:52,974 Best val nmi: 1
2021-09-14 15:37:52,974 Best val r1: 0.8137815126050421
2021-09-14 15:37:52,974 [9]
0.0004 0.0004
it: 1080
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 40.0
    weight_decay: 0
)
2021-09-14 15:38:11,371 Epoch: 11, loss: 0.768, time (seconds): 18.40.
2021-09-14 15:38:11,371 **Validation...**
done collecting prediction
2021-09-14 15:38:18,555 NMI: 100.000
2021-09-14 15:38:19,468 R@1 : 80.773
2021-09-14 15:38:19,508 R@2 : 88.067
2021-09-14 15:38:19,548 R@4 : 92.908
2021-09-14 15:38:19,588 R@8 : 96.269
2021-09-14 15:38:19,588 hmean: 0.8936407586463369
2021-09-14 15:38:19,588 Eval time: 8.22
2021-09-14 15:38:19,589 Best val epoch: 9
2021-09-14 15:38:19,589 Best val hmean: 0.8973313565604152
2021-09-14 15:38:19,589 Best val nmi: 1
2021-09-14 15:38:19,589 Best val r1: 0.8137815126050421
2021-09-14 15:38:19,589 [9]
0.0004 0.0004
it: 1170
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 40.0
    weight_decay: 0
)
2021-09-14 15:38:38,186 Epoch: 12, loss: 0.748, time (seconds): 18.60.
2021-09-14 15:38:38,186 **Validation...**
done collecting prediction
2021-09-14 15:38:45,601 NMI: 100.000
2021-09-14 15:38:46,511 R@1 : 81.109
2021-09-14 15:38:46,549 R@2 : 88.034
2021-09-14 15:38:46,587 R@4 : 93.042
2021-09-14 15:38:46,625 R@8 : 96.403
2021-09-14 15:38:46,625 hmean: 0.8956941351150705
2021-09-14 15:38:46,625 Eval time: 8.44
2021-09-14 15:38:46,626 Best val epoch: 9
2021-09-14 15:38:46,627 Best val hmean: 0.8973313565604152
2021-09-14 15:38:46,627 Best val nmi: 1
2021-09-14 15:38:46,627 Best val r1: 0.8137815126050421
2021-09-14 15:38:46,627 [9]
0.0004 0.0004
it: 1260
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 40.0
    weight_decay: 0
)
2021-09-14 15:39:04,822 Epoch: 13, loss: 0.674, time (seconds): 18.19.
2021-09-14 15:39:04,822 **Validation...**
done collecting prediction
2021-09-14 15:39:12,070 NMI: 100.000
2021-09-14 15:39:12,960 R@1 : 80.471
2021-09-14 15:39:12,998 R@2 : 87.731
2021-09-14 15:39:13,036 R@4 : 93.076
2021-09-14 15:39:13,074 R@8 : 96.303
2021-09-14 15:39:13,074 hmean: 0.8917861799217731
2021-09-14 15:39:13,074 Eval time: 8.25
2021-09-14 15:39:13,075 Best val epoch: 9
2021-09-14 15:39:13,075 Best val hmean: 0.8973313565604152
2021-09-14 15:39:13,075 Best val nmi: 1
2021-09-14 15:39:13,075 Best val r1: 0.8137815126050421
2021-09-14 15:39:13,075 [9]
0.0004 0.0004
it: 1350
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.0004
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 40.0
    weight_decay: 0
)
2021-09-14 15:39:31,257 Epoch: 14, loss: 0.887, time (seconds): 18.18.
2021-09-14 15:39:31,257 **Validation...**
done collecting prediction
2021-09-14 15:39:38,584 NMI: 100.000
2021-09-14 15:39:39,485 R@1 : 80.807
2021-09-14 15:39:39,523 R@2 : 88.067
2021-09-14 15:39:39,561 R@4 : 92.874
2021-09-14 15:39:39,599 R@8 : 96.336
2021-09-14 15:39:39,599 hmean: 0.8938464398587098
2021-09-14 15:39:39,599 Eval time: 8.34
2021-09-14 15:39:39,599 Best val epoch: 9
2021-09-14 15:39:39,599 Best val hmean: 0.8973313565604152
2021-09-14 15:39:39,600 Best val nmi: 1
2021-09-14 15:39:39,600 Best val r1: 0.8137815126050421
2021-09-14 15:39:39,600 [9]
0.0004 4e-05
it: 1440
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0
    weight_decay: 0
)
2021-09-14 15:39:57,927 Epoch: 15, loss: 0.667, time (seconds): 18.33.
2021-09-14 15:39:57,927 **Validation...**
done collecting prediction
2021-09-14 15:40:05,214 NMI: 100.000
2021-09-14 15:40:06,108 R@1 : 81.546
2021-09-14 15:40:06,146 R@2 : 88.168
2021-09-14 15:40:06,184 R@4 : 92.908
2021-09-14 15:40:06,222 R@8 : 96.471
2021-09-14 15:40:06,222 hmean: 0.8983521570079616
2021-09-14 15:40:06,222 Eval time: 8.29
2021-09-14 15:40:06,222 Best val epoch: 15
2021-09-14 15:40:06,222 Best val hmean: 0.8983521570079616
2021-09-14 15:40:06,222 Best val nmi: 1
2021-09-14 15:40:06,222 Best val r1: 0.8154621848739496
2021-09-14 15:40:06,222 [9, 15]
4e-05 4e-05
it: 1530
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0
    weight_decay: 0
)
2021-09-14 15:40:24,240 Epoch: 16, loss: 0.797, time (seconds): 18.02.
2021-09-14 15:40:24,241 **Validation...**
done collecting prediction
2021-09-14 15:40:31,358 NMI: 100.000
2021-09-14 15:40:32,286 R@1 : 81.782
2021-09-14 15:40:32,327 R@2 : 88.303
2021-09-14 15:40:32,366 R@4 : 92.941
2021-09-14 15:40:32,406 R@8 : 96.437
2021-09-14 15:40:32,406 hmean: 0.8997781065088757
2021-09-14 15:40:32,407 Eval time: 8.17
2021-09-14 15:40:32,407 Best val epoch: 16
2021-09-14 15:40:32,407 Best val hmean: 0.8997781065088757
2021-09-14 15:40:32,407 Best val nmi: 1
2021-09-14 15:40:32,407 Best val r1: 0.8178151260504202
2021-09-14 15:40:32,407 [9, 15]
4e-05 4e-05
it: 1620
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0
    weight_decay: 0
)
2021-09-14 15:40:50,689 Epoch: 17, loss: 0.681, time (seconds): 18.28.
2021-09-14 15:40:50,690 **Validation...**
done collecting prediction
2021-09-14 15:40:58,040 NMI: 100.000
2021-09-14 15:40:59,173 R@1 : 81.176
2021-09-14 15:40:59,213 R@2 : 87.966
2021-09-14 15:40:59,253 R@4 : 93.076
2021-09-14 15:40:59,293 R@8 : 96.538
2021-09-14 15:40:59,293 hmean: 0.8961038961038961
2021-09-14 15:40:59,293 Eval time: 8.60
2021-09-14 15:40:59,294 Best val epoch: 16
2021-09-14 15:40:59,295 Best val hmean: 0.8997781065088757
2021-09-14 15:40:59,295 Best val nmi: 1
2021-09-14 15:40:59,295 Best val r1: 0.8178151260504202
2021-09-14 15:40:59,295 [9, 15]
4e-05 4e-05
it: 1710
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0
    weight_decay: 0
)
2021-09-14 15:41:17,696 Epoch: 18, loss: 0.732, time (seconds): 18.40.
2021-09-14 15:41:17,696 **Validation...**
done collecting prediction
2021-09-14 15:41:25,207 NMI: 100.000
2021-09-14 15:41:26,472 R@1 : 81.311
2021-09-14 15:41:26,513 R@2 : 87.832
2021-09-14 15:41:26,553 R@4 : 93.042
2021-09-14 15:41:26,593 R@8 : 96.403
2021-09-14 15:41:26,593 hmean: 0.8969225064886911
2021-09-14 15:41:26,593 Eval time: 8.90
2021-09-14 15:41:26,594 Best val epoch: 16
2021-09-14 15:41:26,594 Best val hmean: 0.8997781065088757
2021-09-14 15:41:26,594 Best val nmi: 1
2021-09-14 15:41:26,594 Best val r1: 0.8178151260504202
2021-09-14 15:41:26,594 [9, 15]
4e-05 4e-05
Gradient overflow.  Skipping step, loss scaler 0 reducing loss scale to 65536.0
it: 1800
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0
    weight_decay: 0
)
2021-09-14 15:41:45,308 Epoch: 19, loss: 0.827, time (seconds): 18.71.
2021-09-14 15:41:45,308 **Validation...**
done collecting prediction
2021-09-14 15:41:52,614 NMI: 100.000
2021-09-14 15:41:53,741 R@1 : 81.176
2021-09-14 15:41:53,781 R@2 : 87.966
2021-09-14 15:41:53,821 R@4 : 93.109
2021-09-14 15:41:53,860 R@8 : 96.437
2021-09-14 15:41:53,860 hmean: 0.8961038961038961
2021-09-14 15:41:53,860 Eval time: 8.55
2021-09-14 15:41:53,861 Best val epoch: 16
2021-09-14 15:41:53,861 Best val hmean: 0.8997781065088757
2021-09-14 15:41:53,861 Best val nmi: 1
2021-09-14 15:41:53,861 Best val r1: 0.8178151260504202
2021-09-14 15:41:53,861 [9, 15]
4e-05 4e-05
it: 1890
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0
    weight_decay: 0
)
2021-09-14 15:42:12,802 Epoch: 20, loss: 0.766, time (seconds): 18.94.
2021-09-14 15:42:12,802 **Validation...**
done collecting prediction
2021-09-14 15:42:20,243 NMI: 100.000
2021-09-14 15:42:21,218 R@1 : 81.277
2021-09-14 15:42:21,258 R@2 : 87.966
2021-09-14 15:42:21,335 R@4 : 93.042
2021-09-14 15:42:21,377 R@8 : 96.269
2021-09-14 15:42:21,377 hmean: 0.896717967735954
2021-09-14 15:42:21,377 Eval time: 8.57
2021-09-14 15:42:21,377 Best val epoch: 16
2021-09-14 15:42:21,377 Best val hmean: 0.8997781065088757
2021-09-14 15:42:21,377 Best val nmi: 1
2021-09-14 15:42:21,378 Best val r1: 0.8178151260504202
2021-09-14 15:42:21,378 [9, 15]
4e-05 4e-05
it: 1980
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4e-05
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0
    weight_decay: 0
)
2021-09-14 15:42:40,025 Epoch: 21, loss: 0.685, time (seconds): 18.65.
2021-09-14 15:42:40,025 **Validation...**
done collecting prediction
2021-09-14 15:42:47,683 NMI: 100.000
2021-09-14 15:42:48,811 R@1 : 81.479
2021-09-14 15:42:48,852 R@2 : 88.168
2021-09-14 15:42:48,893 R@4 : 93.445
2021-09-14 15:42:48,935 R@8 : 96.605
2021-09-14 15:42:48,935 hmean: 0.8979440637155028
2021-09-14 15:42:48,935 Eval time: 8.91
2021-09-14 15:42:48,935 Best val epoch: 16
2021-09-14 15:42:48,935 Best val hmean: 0.8997781065088757
2021-09-14 15:42:48,935 Best val nmi: 1
2021-09-14 15:42:48,936 Best val r1: 0.8178151260504202
2021-09-14 15:42:48,936 [9, 15]
4e-05 4.000000000000001e-06
it: 2070
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-06
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-06
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.4
    weight_decay: 0
)
2021-09-14 15:43:07,512 Epoch: 22, loss: 0.755, time (seconds): 18.58.
2021-09-14 15:43:07,513 **Validation...**
done collecting prediction
2021-09-14 15:43:14,926 NMI: 100.000
2021-09-14 15:43:15,850 R@1 : 81.176
2021-09-14 15:43:15,890 R@2 : 87.933
2021-09-14 15:43:15,930 R@4 : 93.311
2021-09-14 15:43:15,971 R@8 : 96.403
2021-09-14 15:43:15,971 hmean: 0.8961038961038961
2021-09-14 15:43:15,971 Eval time: 8.46
2021-09-14 15:43:15,971 Best val epoch: 16
2021-09-14 15:43:15,971 Best val hmean: 0.8997781065088757
2021-09-14 15:43:15,971 Best val nmi: 1
2021-09-14 15:43:15,971 Best val r1: 0.8178151260504202
2021-09-14 15:43:15,971 [9, 15, 22]
4.000000000000001e-06 4.000000000000001e-06
it: 2160
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-06
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-06
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.4
    weight_decay: 0
)
2021-09-14 15:43:34,531 Epoch: 23, loss: 0.824, time (seconds): 18.56.
2021-09-14 15:43:34,531 **Validation...**
done collecting prediction
2021-09-14 15:43:41,855 NMI: 100.000
2021-09-14 15:43:42,946 R@1 : 81.345
2021-09-14 15:43:42,986 R@2 : 87.966
2021-09-14 15:43:43,027 R@4 : 93.244
2021-09-14 15:43:43,067 R@8 : 96.101
2021-09-14 15:43:43,067 hmean: 0.897126969416126
2021-09-14 15:43:43,067 Eval time: 8.54
2021-09-14 15:43:43,068 Best val epoch: 16
2021-09-14 15:43:43,068 Best val hmean: 0.8997781065088757
2021-09-14 15:43:43,068 Best val nmi: 1
2021-09-14 15:43:43,068 Best val r1: 0.8178151260504202
2021-09-14 15:43:43,068 [9, 15, 22]
4.000000000000001e-06 4.000000000000001e-06
it: 2250
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-06
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-06
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.4
    weight_decay: 0
)
2021-09-14 15:44:01,217 Epoch: 24, loss: 0.819, time (seconds): 18.15.
2021-09-14 15:44:01,217 **Validation...**
done collecting prediction
2021-09-14 15:44:08,579 NMI: 100.000
2021-09-14 15:44:09,533 R@1 : 81.378
2021-09-14 15:44:09,572 R@2 : 88.067
2021-09-14 15:44:09,610 R@4 : 92.975
2021-09-14 15:44:09,648 R@8 : 96.538
2021-09-14 15:44:09,649 hmean: 0.8973313565604152
2021-09-14 15:44:09,649 Eval time: 8.43
2021-09-14 15:44:09,650 Best val epoch: 16
2021-09-14 15:44:09,650 Best val hmean: 0.8997781065088757
2021-09-14 15:44:09,650 Best val nmi: 1
2021-09-14 15:44:09,650 Best val r1: 0.8178151260504202
2021-09-14 15:44:09,650 [9, 15, 22]
4.000000000000001e-06 4.000000000000001e-06
it: 2340
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-06
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-06
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.4
    weight_decay: 0
)
2021-09-14 15:44:27,945 Epoch: 25, loss: 0.788, time (seconds): 18.29.
2021-09-14 15:44:27,945 **Validation...**
done collecting prediction
2021-09-14 15:44:35,123 NMI: 100.000
2021-09-14 15:44:36,056 R@1 : 81.479
2021-09-14 15:44:36,096 R@2 : 87.798
2021-09-14 15:44:36,136 R@4 : 93.109
2021-09-14 15:44:36,176 R@8 : 96.336
2021-09-14 15:44:36,176 hmean: 0.8979440637155028
2021-09-14 15:44:36,176 Eval time: 8.23
2021-09-14 15:44:36,176 Best val epoch: 16
2021-09-14 15:44:36,176 Best val hmean: 0.8997781065088757
2021-09-14 15:44:36,176 Best val nmi: 1
2021-09-14 15:44:36,176 Best val r1: 0.8178151260504202
2021-09-14 15:44:36,176 [9, 15, 22]
4.000000000000001e-06 4.000000000000001e-06
it: 2430
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-06
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-06
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.4
    weight_decay: 0
)
2021-09-14 15:44:54,340 Epoch: 26, loss: 0.765, time (seconds): 18.16.
2021-09-14 15:44:54,340 **Validation...**
done collecting prediction
2021-09-14 15:45:01,659 NMI: 100.000
2021-09-14 15:45:02,596 R@1 : 81.546
2021-09-14 15:45:02,636 R@2 : 88.370
2021-09-14 15:45:02,676 R@4 : 93.042
2021-09-14 15:45:02,716 R@8 : 96.336
2021-09-14 15:45:02,716 hmean: 0.8983521570079616
2021-09-14 15:45:02,716 Eval time: 8.38
2021-09-14 15:45:02,716 Best val epoch: 16
2021-09-14 15:45:02,716 Best val hmean: 0.8997781065088757
2021-09-14 15:45:02,716 Best val nmi: 1
2021-09-14 15:45:02,716 Best val r1: 0.8178151260504202
2021-09-14 15:45:02,716 [9, 15, 22]
4.000000000000001e-06 4.000000000000001e-07
it: 2520
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-07
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-07
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.04000000000000001
    weight_decay: 0
)
2021-09-14 15:45:20,921 Epoch: 27, loss: 0.755, time (seconds): 18.20.
2021-09-14 15:45:20,921 **Validation...**
done collecting prediction
2021-09-14 15:45:28,399 NMI: 100.000
2021-09-14 15:45:29,288 R@1 : 81.513
2021-09-14 15:45:29,328 R@2 : 88.067
2021-09-14 15:45:29,368 R@4 : 93.109
2021-09-14 15:45:29,408 R@8 : 96.370
2021-09-14 15:45:29,408 hmean: 0.8981481481481481
2021-09-14 15:45:29,408 Eval time: 8.49
2021-09-14 15:45:29,408 Best val epoch: 16
2021-09-14 15:45:29,408 Best val hmean: 0.8997781065088757
2021-09-14 15:45:29,408 Best val nmi: 1
2021-09-14 15:45:29,408 Best val r1: 0.8178151260504202
2021-09-14 15:45:29,408 [9, 15, 22, 27]
4.000000000000001e-07 4.000000000000001e-07
it: 2610
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-07
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-07
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.04000000000000001
    weight_decay: 0
)
2021-09-14 15:45:47,778 Epoch: 28, loss: 0.762, time (seconds): 18.37.
2021-09-14 15:45:47,778 **Validation...**
done collecting prediction
2021-09-14 15:45:55,173 NMI: 100.000
2021-09-14 15:45:56,090 R@1 : 81.513
2021-09-14 15:45:56,130 R@2 : 87.832
2021-09-14 15:45:56,169 R@4 : 92.941
2021-09-14 15:45:56,209 R@8 : 96.269
2021-09-14 15:45:56,209 hmean: 0.8981481481481481
2021-09-14 15:45:56,209 Eval time: 8.43
2021-09-14 15:45:56,209 Best val epoch: 16
2021-09-14 15:45:56,209 Best val hmean: 0.8997781065088757
2021-09-14 15:45:56,209 Best val nmi: 1
2021-09-14 15:45:56,209 Best val r1: 0.8178151260504202
2021-09-14 15:45:56,209 [9, 15, 22, 27]
4.000000000000001e-07 4.000000000000001e-07
it: 2700
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-07
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-07
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.04000000000000001
    weight_decay: 0
)
2021-09-14 15:46:14,510 Epoch: 29, loss: 0.745, time (seconds): 18.30.
2021-09-14 15:46:14,510 **Validation...**
done collecting prediction
2021-09-14 15:46:21,755 NMI: 100.000
2021-09-14 15:46:22,688 R@1 : 80.975
2021-09-14 15:46:22,730 R@2 : 87.597
2021-09-14 15:46:22,771 R@4 : 93.042
2021-09-14 15:46:22,812 R@8 : 96.538
2021-09-14 15:46:22,812 hmean: 0.8948736998514115
2021-09-14 15:46:22,812 Eval time: 8.30
2021-09-14 15:46:22,812 Best val epoch: 16
2021-09-14 15:46:22,812 Best val hmean: 0.8997781065088757
2021-09-14 15:46:22,812 Best val nmi: 1
2021-09-14 15:46:22,812 Best val r1: 0.8178151260504202
2021-09-14 15:46:22,812 [9, 15, 22, 27]
4.000000000000001e-07 4.000000000000001e-07
it: 2790
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-07
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-07
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.04000000000000001
    weight_decay: 0
)
2021-09-14 15:46:42,180 Epoch: 30, loss: 0.677, time (seconds): 19.37.
2021-09-14 15:46:42,180 **Validation...**
done collecting prediction
2021-09-14 15:46:49,730 NMI: 100.000
2021-09-14 15:46:50,758 R@1 : 81.008
2021-09-14 15:46:50,800 R@2 : 88.000
2021-09-14 15:46:50,840 R@4 : 93.277
2021-09-14 15:46:50,881 R@8 : 96.370
2021-09-14 15:46:50,881 hmean: 0.8950789229340761
2021-09-14 15:46:50,881 Eval time: 8.70
2021-09-14 15:46:50,882 Best val epoch: 16
2021-09-14 15:46:50,882 Best val hmean: 0.8997781065088757
2021-09-14 15:46:50,882 Best val nmi: 1
2021-09-14 15:46:50,882 Best val r1: 0.8178151260504202
2021-09-14 15:46:50,882 [9, 15, 22, 27]
4.000000000000001e-07 4.000000000000001e-07
it: 2880
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-07
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000001e-07
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.04000000000000001
    weight_decay: 0
)
2021-09-14 15:47:09,836 Epoch: 31, loss: 0.731, time (seconds): 18.95.
2021-09-14 15:47:09,836 **Validation...**
done collecting prediction
2021-09-14 15:47:17,502 NMI: 100.000
2021-09-14 15:47:18,400 R@1 : 81.244
2021-09-14 15:47:18,441 R@2 : 88.067
2021-09-14 15:47:18,480 R@4 : 93.076
2021-09-14 15:47:18,520 R@8 : 96.403
2021-09-14 15:47:18,520 hmean: 0.896513353115727
2021-09-14 15:47:18,521 Eval time: 8.68
2021-09-14 15:47:18,522 Best val epoch: 16
2021-09-14 15:47:18,522 Best val hmean: 0.8997781065088757
2021-09-14 15:47:18,522 Best val nmi: 1
2021-09-14 15:47:18,522 Best val r1: 0.8178151260504202
2021-09-14 15:47:18,522 [9, 15, 22, 27]
4.000000000000001e-07 4.0000000000000014e-08
it: 2970
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0000000000000014e-08
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0000000000000014e-08
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004000000000000001
    weight_decay: 0
)
2021-09-14 15:47:37,259 Epoch: 32, loss: 0.709, time (seconds): 18.74.
2021-09-14 15:47:37,259 **Validation...**
done collecting prediction
2021-09-14 15:47:44,815 NMI: 100.000
2021-09-14 15:47:45,771 R@1 : 81.210
2021-09-14 15:47:45,811 R@2 : 88.303
2021-09-14 15:47:45,852 R@4 : 93.412
2021-09-14 15:47:45,892 R@8 : 96.403
2021-09-14 15:47:45,892 hmean: 0.8963086625857911
2021-09-14 15:47:45,892 Eval time: 8.63
2021-09-14 15:47:45,893 Best val epoch: 16
2021-09-14 15:47:45,894 Best val hmean: 0.8997781065088757
2021-09-14 15:47:45,894 Best val nmi: 1
2021-09-14 15:47:45,894 Best val r1: 0.8178151260504202
2021-09-14 15:47:45,894 [9, 15, 22, 27, 32]
4.0000000000000014e-08 4.0000000000000014e-08
it: 3060
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0000000000000014e-08
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0000000000000014e-08
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004000000000000001
    weight_decay: 0
)
2021-09-14 15:48:05,102 Epoch: 33, loss: 0.840, time (seconds): 19.21.
2021-09-14 15:48:05,102 **Validation...**
done collecting prediction
2021-09-14 15:48:12,688 NMI: 100.000
2021-09-14 15:48:13,614 R@1 : 81.277
2021-09-14 15:48:13,652 R@2 : 87.630
2021-09-14 15:48:13,690 R@4 : 93.008
2021-09-14 15:48:13,729 R@8 : 96.403
2021-09-14 15:48:13,729 hmean: 0.896717967735954
2021-09-14 15:48:13,729 Eval time: 8.63
2021-09-14 15:48:13,730 Best val epoch: 16
2021-09-14 15:48:13,730 Best val hmean: 0.8997781065088757
2021-09-14 15:48:13,730 Best val nmi: 1
2021-09-14 15:48:13,730 Best val r1: 0.8178151260504202
2021-09-14 15:48:13,730 [9, 15, 22, 27, 32]
4.0000000000000014e-08 4.0000000000000014e-08
it: 3150
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0000000000000014e-08
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0000000000000014e-08
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004000000000000001
    weight_decay: 0
)
2021-09-14 15:48:32,067 Epoch: 34, loss: 0.787, time (seconds): 18.34.
2021-09-14 15:48:32,067 **Validation...**
done collecting prediction
2021-09-14 15:48:39,650 NMI: 100.000
2021-09-14 15:48:40,735 R@1 : 81.076
2021-09-14 15:48:40,775 R@2 : 87.933
2021-09-14 15:48:40,816 R@4 : 92.975
2021-09-14 15:48:40,855 R@8 : 96.471
2021-09-14 15:48:40,856 hmean: 0.8954891405234825
2021-09-14 15:48:40,856 Eval time: 8.79
2021-09-14 15:48:40,856 Best val epoch: 16
2021-09-14 15:48:40,856 Best val hmean: 0.8997781065088757
2021-09-14 15:48:40,856 Best val nmi: 1
2021-09-14 15:48:40,856 Best val r1: 0.8178151260504202
2021-09-14 15:48:40,856 [9, 15, 22, 27, 32]
4.0000000000000014e-08 4.0000000000000014e-08
it: 3240
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0000000000000014e-08
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0000000000000014e-08
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004000000000000001
    weight_decay: 0
)
2021-09-14 15:48:59,369 Epoch: 35, loss: 0.692, time (seconds): 18.51.
2021-09-14 15:48:59,369 **Validation...**
done collecting prediction
2021-09-14 15:49:06,660 NMI: 100.000
2021-09-14 15:49:07,579 R@1 : 80.874
2021-09-14 15:49:07,619 R@2 : 87.832
2021-09-14 15:49:07,659 R@4 : 92.874
2021-09-14 15:49:07,699 R@8 : 96.269
2021-09-14 15:49:07,700 hmean: 0.8942575729418323
2021-09-14 15:49:07,700 Eval time: 8.33
2021-09-14 15:49:07,700 Best val epoch: 16
2021-09-14 15:49:07,700 Best val hmean: 0.8997781065088757
2021-09-14 15:49:07,700 Best val nmi: 1
2021-09-14 15:49:07,700 Best val r1: 0.8178151260504202
2021-09-14 15:49:07,700 [9, 15, 22, 27, 32]
4.0000000000000014e-08 4.0000000000000014e-08
it: 3330
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0000000000000014e-08
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.0000000000000014e-08
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.004000000000000001
    weight_decay: 0
)
2021-09-14 15:49:26,121 Epoch: 36, loss: 0.691, time (seconds): 18.42.
2021-09-14 15:49:26,121 **Validation...**
done collecting prediction
2021-09-14 15:49:33,421 NMI: 100.000
2021-09-14 15:49:34,407 R@1 : 81.176
2021-09-14 15:49:34,447 R@2 : 88.034
2021-09-14 15:49:34,488 R@4 : 93.109
2021-09-14 15:49:34,529 R@8 : 96.336
2021-09-14 15:49:34,529 hmean: 0.8961038961038961
2021-09-14 15:49:34,529 Eval time: 8.41
2021-09-14 15:49:34,530 Best val epoch: 16
2021-09-14 15:49:34,530 Best val hmean: 0.8997781065088757
2021-09-14 15:49:34,530 Best val nmi: 1
2021-09-14 15:49:34,530 Best val r1: 0.8178151260504202
2021-09-14 15:49:34,530 [9, 15, 22, 27, 32]
4.0000000000000014e-08 4.000000000000002e-09
it: 3420
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000002e-09
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000002e-09
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.00040000000000000013
    weight_decay: 0
)
2021-09-14 15:49:52,989 Epoch: 37, loss: 0.811, time (seconds): 18.46.
2021-09-14 15:49:52,990 **Validation...**
done collecting prediction
2021-09-14 15:50:00,352 NMI: 100.000
2021-09-14 15:50:01,311 R@1 : 81.076
2021-09-14 15:50:01,351 R@2 : 87.664
2021-09-14 15:50:01,391 R@4 : 93.143
2021-09-14 15:50:01,432 R@8 : 96.471
2021-09-14 15:50:01,432 hmean: 0.8954891405234825
2021-09-14 15:50:01,432 Eval time: 8.44
2021-09-14 15:50:01,433 Best val epoch: 16
2021-09-14 15:50:01,433 Best val hmean: 0.8997781065088757
2021-09-14 15:50:01,433 Best val nmi: 1
2021-09-14 15:50:01,433 Best val r1: 0.8178151260504202
2021-09-14 15:50:01,433 [9, 15, 22, 27, 32, 37]
4.000000000000002e-09 4.000000000000002e-09
it: 3510
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000002e-09
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000002e-09
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.00040000000000000013
    weight_decay: 0
)
2021-09-14 15:50:19,806 Epoch: 38, loss: 0.731, time (seconds): 18.37.
2021-09-14 15:50:19,807 **Validation...**
done collecting prediction
2021-09-14 15:50:27,175 NMI: 100.000
2021-09-14 15:50:28,225 R@1 : 81.109
2021-09-14 15:50:28,266 R@2 : 88.067
2021-09-14 15:50:28,307 R@4 : 93.345
2021-09-14 15:50:28,348 R@8 : 96.403
2021-09-14 15:50:28,348 hmean: 0.8956941351150705
2021-09-14 15:50:28,348 Eval time: 8.54
2021-09-14 15:50:28,348 Best val epoch: 16
2021-09-14 15:50:28,348 Best val hmean: 0.8997781065088757
2021-09-14 15:50:28,348 Best val nmi: 1
2021-09-14 15:50:28,348 Best val r1: 0.8178151260504202
2021-09-14 15:50:28,348 [9, 15, 22, 27, 32, 37]
4.000000000000002e-09 4.000000000000002e-09
it: 3600
Adam (
Parameter Group 0
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000002e-09
    weight_decay: 0

Parameter Group 1
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 4.000000000000002e-09
    weight_decay: 0

Parameter Group 2
    amsgrad: False
    betas: (0.9, 0.999)
    eps: 1.0
    lr: 0.00040000000000000013
    weight_decay: 0
)
2021-09-14 15:50:46,873 Epoch: 39, loss: 0.903, time (seconds): 18.52.
2021-09-14 15:50:46,874 **Validation...**
done collecting prediction
2021-09-14 15:50:54,384 NMI: 100.000
2021-09-14 15:50:55,323 R@1 : 81.681
2021-09-14 15:50:55,362 R@2 : 88.000
2021-09-14 15:50:55,402 R@4 : 92.672
2021-09-14 15:50:55,441 R@8 : 96.471
2021-09-14 15:50:55,441 hmean: 0.8991674375578168
2021-09-14 15:50:55,441 Eval time: 8.57
2021-09-14 15:50:55,442 Best val epoch: 16
2021-09-14 15:50:55,442 Best val hmean: 0.8997781065088757
2021-09-14 15:50:55,442 Best val nmi: 1
2021-09-14 15:50:55,442 Best val r1: 0.8178151260504202
2021-09-14 15:50:55,442 [9, 15, 22, 27, 32, 37]
lr_steps [9, 15, 22, 27, 32, 37]
2021-09-14 15:50:55,443 Total training time (minutes): 19.44.