Arch: resnet50_pt
Bs trn: 128
Bs val: 128
Hidden dim: 256
Dataset: celebA
Resample class: 
Slice with: rep
Rep cluster method: gmm
Num anchor: 32
Num positive: 32
Num negative: 32
Num negative easy: 0
Weight anc by loss: False
Weight pos by loss: False
Weight neg by loss: False
Anc loss temp: 0.5
Pos loss temp: 0.5
Neg loss temp: 0.5
Data wide pos: False
Target sample ratio: 1
Balance targets: False
Additional negatives: False
Hard negative factor: 0
Full contrastive: False
Train encoder: False
No projection head: False
Projection dim: 128
Batch factor: None
Temperature: 0.05
Single pos: False
Supervised linear scale up: False
Supervised update delay: 0
Contrastive weight: 0.5
Classifier update interval: 8
Optim: sgd
Max epoch: 5
Lr: 0.0001
Momentum: 0.9
Weight decay: 0.1
Weight decay c: 0.1
Stopping window: 30
Load encoder: 
Freeze encoder: False
Finetune epochs: 0
Clip grad norm: False
Lr scheduler classifier: 
Lr scheduler: 
Grad clip grad norm: False
Erm: False
Erm only: False
Pretrained spurious path: 
Max epoch s: 1
Bs trn s: 32
Lr s: 0.001
Momentum s: 0.9
Weight decay s: 0.0005
Slice temp: 10
Log loss interval: 10
Checkpoint interval: 50
Grad checkpoint interval: 50
Log visual interval: 100
Log grad visual interval: 50
Verbose: True
Seed: 34
Replicate: 0
No cuda: False
Resume: False
New slice: False
Num workers: 12
Evaluate: False
Data cmap: hsv
Test cmap: 
P correlation: 0.9
P corr by class: None
Train classes: ['blond', 'nonblond']
Train class ratios: None
Test shift: random
Flipped: False
Q: 0.7
Pretrained bmodel: False
Cosine: False
Exp: stage_one_erm
Supervised contrast: True
Prioritize spurious pos: False
Contrastive type: cnc
Compute auroc: False
Model type: resnet50_pt_cnc
Criterion: cross_entropy
Pretrained: False
Max grad norm: 1.0
Adam epsilon: 1e-08
Warmup steps: 0
Max grad norm s: 1.0
Adam epsilon s: 1e-08
Warmup steps s: 0
Grad max grad norm: 1.0
Grad adam epsilon: 1e-08
Grad warmup steps: 0
Device: cuda
Img file type: .png
Display image: False
Image path: ./images/celebA/celebA/config/contrastive_umaps
Log interval: 1
Log path: ./logs/celebA/config
Results path: ./results/celebA/config
Model path: ./model/celebA/config
Loss factor: 1
Supersample labels: False
Subsample labels: False
Weigh slice samples by loss: True
Val split: 0.2
Spurious train split: 0.2
Subsample groups: False
Train method: sc
Max robust acc: -1
Max robust epoch: -1
Max robust group acc: (None, None)
Root dir: ./datasets/data/CelebA/
Target name: Blond_Hair
Confounder names: ['Male']
Image mean: 0.449
Image std: 0.226
Augment data: False
Task: celebA
Num classes: 2
Experiment configs: config
Experiment name: cnc-celebA-sw=re-na=32-np=32-nn=32-nne=0-tsr=1-t=0.05-bf=None-cw=0.5-sud=0-me=5-bst=128-o=sgd-lr=0.0001-mo=0.9-wd=0.1-wdc=0.1-spur-me=1-bst=32-lr=0.001-mo=0.9-wd=0.0005-sts=0.2-s=34-r=0
Mi resampled: None

Loading checkpoints for train split:
[-1 -1 -1 ... -1 -1 -1]
<class 'numpy.ndarray'>
[0 1 2 3] [71629 66874 22880  1387]
Loading checkpoints for val split:
[-1 -1 -1 ... -1  1 -1]
<class 'numpy.ndarray'>
[0 1 2 3] [8535 8276 2874  182]
Loading checkpoints for test split:
[-1 -1 -1 ... -1 -1  1]
<class 'numpy.ndarray'>
[0 1 2 3] [9767 7535 2480  180]
Train dataset:
    Blond_Hair = 0, Male = 0 : n = 71629
    Blond_Hair = 0, Male = 1 : n = 66874
    Blond_Hair = 1, Male = 0 : n = 22880
    Blond_Hair = 1, Male = 1 : n = 1387
Val dataset:
    Blond_Hair = 0, Male = 0 : n = 8535
    Blond_Hair = 0, Male = 1 : n = 8276
    Blond_Hair = 1, Male = 0 : n = 2874
    Blond_Hair = 1, Male = 1 : n = 182
Test dataset:
    Blond_Hair = 0, Male = 0 : n = 9767
    Blond_Hair = 0, Male = 1 : n = 7535
    Blond_Hair = 1, Male = 0 : n = 2480
    Blond_Hair = 1, Male = 1 : n = 180
Pretrained model loaded from 
Epoch:   1 | Train Loss: 0.000 | Train Acc: 84.810 | Val Loss: 0.003 | Val Acc: 84.618
Training:
Accuracies by groups:
0, 0  acc: 71309 / 71629 =  99.553
0, 1  acc: 66616 / 66874 =  99.614
1, 0  acc:   118 / 22880 =   0.516
1, 1  acc:     3 /  1387 =   0.216
--------------------------------------
Average acc: 138046 / 162770 =  84.810
Robust  acc:     3 /  1387 =   0.216
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8535 /  8535 = 100.000
0, 1  acc:  8276 /  8276 = 100.000
1, 0  acc:     0 /  2874 =   0.000
1, 1  acc:     0 /   182 =   0.000
------------------------------------
Average acc: 16811 / 19867 =  84.618
Robust  acc:     0 /  2874 =   0.000
------------------------------------
Save biased model at epoch 0
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch0_seed34.pt
New max average-worst acc gap: 84.61770775658127
bias model - Saving best checkpoint at epoch 0
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_worst_avg_gap_best_epoch0_seed34.pt
-------------------------------------------
Avg Test Loss: 0.003 | Avg Test Acc: 86.675
Robust Acc: 0.000 | Best Acc: 100.000
-------------------------------------
Training, Epoch 0:
Accuracies by groups:
0, 0  acc:  9767 /  9767 = 100.000
0, 1  acc:  7535 /  7535 = 100.000
1, 0  acc:     0 /  2480 =   0.000
1, 1  acc:     0 /   180 =   0.000
------------------------------------
Average acc: 17302 / 19962 =  86.675
Robust  acc:     0 /  2480 =   0.000
------------------------------------
Accuracies by groups:
0, 0  acc:  9767 /  9767 = 100.000
0, 1  acc:  7535 /  7535 = 100.000
1, 0  acc:     0 /  2480 =   0.000
1, 1  acc:     0 /   180 =   0.000
------------------------------------
Average acc: 17302 / 19962 =  86.675
Robust  acc:     0 /  2480 =   0.000
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9767 /  9767 = 100.000
0, 1  acc:  7535 /  7535 = 100.000
1, 0  acc:     0 /  2480 =   0.000
1, 1  acc:     0 /   180 =   0.000
------------------------------------
Average acc: 17302 / 19962 =  86.675
Robust  acc:     0 /  2480 =   0.000
------------------------------------
Epoch:   2 | Train Loss: 0.001 | Train Acc: 87.437 | Val Loss: 0.002 | Val Acc: 92.037
Training:
Accuracies by groups:
0, 0  acc: 71270 / 71629 =  99.499
0, 1  acc: 66869 / 66874 =  99.993
1, 0  acc:  4169 / 22880 =  18.221
1, 1  acc:    14 /  1387 =   1.009
--------------------------------------
Average acc: 142322 / 162770 =  87.437
Robust  acc:    14 /  1387 =   1.009
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8277 /  8535 =  96.977
0, 1  acc:  8274 /  8276 =  99.976
1, 0  acc:  1727 /  2874 =  60.090
1, 1  acc:     7 /   182 =   3.846
------------------------------------
Average acc: 18285 / 19867 =  92.037
Robust  acc:     7 /   182 =   3.846
------------------------------------
Save biased model at epoch 1
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch1_seed34.pt
New max average-worst acc gap: 88.19089251212874
bias model - Saving best checkpoint at epoch 1
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_worst_avg_gap_best_epoch1_seed34.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 92.506
Robust Acc: 7.778 | Best Acc: 100.000
-------------------------------------
Training, Epoch 1:
Accuracies by groups:
0, 0  acc:  9573 /  9767 =  98.014
0, 1  acc:  7535 /  7535 = 100.000
1, 0  acc:  1344 /  2480 =  54.194
1, 1  acc:    14 /   180 =   7.778
------------------------------------
Average acc: 18466 / 19962 =  92.506
Robust  acc:    14 /   180 =   7.778
------------------------------------
Accuracies by groups:
0, 0  acc:  9573 /  9767 =  98.014
0, 1  acc:  7535 /  7535 = 100.000
1, 0  acc:  1344 /  2480 =  54.194
1, 1  acc:    14 /   180 =   7.778
------------------------------------
Average acc: 18466 / 19962 =  92.506
Robust  acc:    14 /   180 =   7.778
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9573 /  9767 =  98.014
0, 1  acc:  7535 /  7535 = 100.000
1, 0  acc:  1344 /  2480 =  54.194
1, 1  acc:    14 /   180 =   7.778
------------------------------------
Average acc: 18466 / 19962 =  92.506
Robust  acc:    14 /   180 =   7.778
------------------------------------
Epoch:   3 | Train Loss: 0.000 | Train Acc: 93.260 | Val Loss: 0.001 | Val Acc: 93.950
Training:
Accuracies by groups:
0, 0  acc: 69240 / 71629 =  96.665
0, 1  acc: 66739 / 66874 =  99.798
1, 0  acc: 15621 / 22880 =  68.274
1, 1  acc:   199 /  1387 =  14.348
--------------------------------------
Average acc: 151799 / 162770 =  93.260
Robust  acc:   199 /  1387 =  14.348
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8216 /  8535 =  96.262
0, 1  acc:  8262 /  8276 =  99.831
1, 0  acc:  2165 /  2874 =  75.331
1, 1  acc:    22 /   182 =  12.088
------------------------------------
Average acc: 18665 / 19867 =  93.950
Robust  acc:    22 /   182 =  12.088
------------------------------------
Save biased model at epoch 2
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch2_seed34.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 94.189
Robust Acc: 17.222 | Best Acc: 99.934
-------------------------------------
Training, Epoch 2:
Accuracies by groups:
0, 0  acc:  9513 /  9767 =  97.399
0, 1  acc:  7530 /  7535 =  99.934
1, 0  acc:  1728 /  2480 =  69.677
1, 1  acc:    31 /   180 =  17.222
------------------------------------
Average acc: 18802 / 19962 =  94.189
Robust  acc:    31 /   180 =  17.222
------------------------------------
Accuracies by groups:
0, 0  acc:  9513 /  9767 =  97.399
0, 1  acc:  7530 /  7535 =  99.934
1, 0  acc:  1728 /  2480 =  69.677
1, 1  acc:    31 /   180 =  17.222
------------------------------------
Average acc: 18802 / 19962 =  94.189
Robust  acc:    31 /   180 =  17.222
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9513 /  9767 =  97.399
0, 1  acc:  7530 /  7535 =  99.934
1, 0  acc:  1728 /  2480 =  69.677
1, 1  acc:    31 /   180 =  17.222
------------------------------------
Average acc: 18802 / 19962 =  94.189
Robust  acc:    31 /   180 =  17.222
------------------------------------
Epoch:   4 | Train Loss: 0.000 | Train Acc: 94.267 | Val Loss: 0.001 | Val Acc: 94.473
Training:
Accuracies by groups:
0, 0  acc: 68885 / 71629 =  96.169
0, 1  acc: 66614 / 66874 =  99.611
1, 0  acc: 17624 / 22880 =  77.028
1, 1  acc:   315 /  1387 =  22.711
--------------------------------------
Average acc: 153438 / 162770 =  94.267
Robust  acc:   315 /  1387 =  22.711
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8171 /  8535 =  95.735
0, 1  acc:  8254 /  8276 =  99.734
1, 0  acc:  2314 /  2874 =  80.515
1, 1  acc:    30 /   182 =  16.484
------------------------------------
Average acc: 18769 / 19867 =  94.473
Robust  acc:    30 /   182 =  16.484
------------------------------------
Save biased model at epoch 3
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch3_seed34.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 94.850
Robust Acc: 25.000 | Best Acc: 99.774
-------------------------------------
Training, Epoch 3:
Accuracies by groups:
0, 0  acc:  9468 /  9767 =  96.939
0, 1  acc:  7518 /  7535 =  99.774
1, 0  acc:  1903 /  2480 =  76.734
1, 1  acc:    45 /   180 =  25.000
------------------------------------
Average acc: 18934 / 19962 =  94.850
Robust  acc:    45 /   180 =  25.000
------------------------------------
Accuracies by groups:
0, 0  acc:  9468 /  9767 =  96.939
0, 1  acc:  7518 /  7535 =  99.774
1, 0  acc:  1903 /  2480 =  76.734
1, 1  acc:    45 /   180 =  25.000
------------------------------------
Average acc: 18934 / 19962 =  94.850
Robust  acc:    45 /   180 =  25.000
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9468 /  9767 =  96.939
0, 1  acc:  7518 /  7535 =  99.774
1, 0  acc:  1903 /  2480 =  76.734
1, 1  acc:    45 /   180 =  25.000
------------------------------------
Average acc: 18934 / 19962 =  94.850
Robust  acc:    45 /   180 =  25.000
------------------------------------
Epoch:   5 | Train Loss: 0.000 | Train Acc: 94.667 | Val Loss: 0.001 | Val Acc: 94.790
Training:
Accuracies by groups:
0, 0  acc: 68787 / 71629 =  96.032
0, 1  acc: 66575 / 66874 =  99.553
1, 0  acc: 18345 / 22880 =  80.179
1, 1  acc:   382 /  1387 =  27.541
--------------------------------------
Average acc: 154089 / 162770 =  94.667
Robust  acc:   382 /  1387 =  27.541
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8166 /  8535 =  95.677
0, 1  acc:  8254 /  8276 =  99.734
1, 0  acc:  2373 /  2874 =  82.568
1, 1  acc:    39 /   182 =  21.429
------------------------------------
Average acc: 18832 / 19867 =  94.790
Robust  acc:    39 /   182 =  21.429
------------------------------------
Save biased model at epoch 4
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch4_seed34.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 95.241
Robust Acc: 28.889 | Best Acc: 99.748
-------------------------------------
Training, Epoch 4:
Accuracies by groups:
0, 0  acc:  9459 /  9767 =  96.847
0, 1  acc:  7516 /  7535 =  99.748
1, 0  acc:  1985 /  2480 =  80.040
1, 1  acc:    52 /   180 =  28.889
------------------------------------
Average acc: 19012 / 19962 =  95.241
Robust  acc:    52 /   180 =  28.889
------------------------------------
Accuracies by groups:
0, 0  acc:  9459 /  9767 =  96.847
0, 1  acc:  7516 /  7535 =  99.748
1, 0  acc:  1985 /  2480 =  80.040
1, 1  acc:    52 /   180 =  28.889
------------------------------------
Average acc: 19012 / 19962 =  95.241
Robust  acc:    52 /   180 =  28.889
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9459 /  9767 =  96.847
0, 1  acc:  7516 /  7535 =  99.748
1, 0  acc:  1985 /  2480 =  80.040
1, 1  acc:    52 /   180 =  28.889
------------------------------------
Average acc: 19012 / 19962 =  95.241
Robust  acc:    52 /   180 =  28.889
------------------------------------
replace: True
Checkpoint saved at ./model/celebA/config/bias-end_seed34.pt
training biased model is done
