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: 49
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=49-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: 84.579 | Val Loss: 0.003 | Val Acc: 84.618
Training:
Accuracies by groups:
0, 0  acc: 71120 / 71629 =  99.289
0, 1  acc: 66349 / 66874 =  99.215
1, 0  acc:   185 / 22880 =   0.809
1, 1  acc:    16 /  1387 =   1.154
--------------------------------------
Average acc: 137670 / 162770 =  84.579
Robust  acc:   185 / 22880 =   0.809
--------------------------------------
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_seed49.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_seed49.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: 87.776 | Val Loss: 0.001 | Val Acc: 92.279
Training:
Accuracies by groups:
0, 0  acc: 71165 / 71629 =  99.352
0, 1  acc: 66868 / 66874 =  99.991
1, 0  acc:  4827 / 22880 =  21.097
1, 1  acc:    13 /  1387 =   0.937
--------------------------------------
Average acc: 142873 / 162770 =  87.776
Robust  acc:    13 /  1387 =   0.937
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8251 /  8535 =  96.673
0, 1  acc:  8276 /  8276 = 100.000
1, 0  acc:  1800 /  2874 =  62.630
1, 1  acc:     6 /   182 =   3.297
------------------------------------
Average acc: 18333 / 19867 =  92.279
Robust  acc:     6 /   182 =   3.297
------------------------------------
Save biased model at epoch 1
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch1_seed49.pt
New max average-worst acc gap: 88.98194974603088
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_seed49.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 92.796
Robust Acc: 7.222 | Best Acc: 99.987
------------------------------------
Training, Epoch 1:
Accuracies by groups:
0, 0  acc:  9570 /  9767 =  97.983
0, 1  acc:  7534 /  7535 =  99.987
1, 0  acc:  1407 /  2480 =  56.734
1, 1  acc:    13 /   180 =   7.222
------------------------------------
Average acc: 18524 / 19962 =  92.796
Robust  acc:    13 /   180 =   7.222
------------------------------------
Accuracies by groups:
0, 0  acc:  9570 /  9767 =  97.983
0, 1  acc:  7534 /  7535 =  99.987
1, 0  acc:  1407 /  2480 =  56.734
1, 1  acc:    13 /   180 =   7.222
------------------------------------
Average acc: 18524 / 19962 =  92.796
Robust  acc:    13 /   180 =   7.222
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9570 /  9767 =  97.983
0, 1  acc:  7534 /  7535 =  99.987
1, 0  acc:  1407 /  2480 =  56.734
1, 1  acc:    13 /   180 =   7.222
------------------------------------
Average acc: 18524 / 19962 =  92.796
Robust  acc:    13 /   180 =   7.222
------------------------------------
Epoch:   3 | Train Loss: 0.000 | Train Acc: 93.352 | Val Loss: 0.001 | Val Acc: 94.101
Training:
Accuracies by groups:
0, 0  acc: 69277 / 71629 =  96.716
0, 1  acc: 66743 / 66874 =  99.804
1, 0  acc: 15722 / 22880 =  68.715
1, 1  acc:   207 /  1387 =  14.924
--------------------------------------
Average acc: 151949 / 162770 =  93.352
Robust  acc:   207 /  1387 =  14.924
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8148 /  8535 =  95.466
0, 1  acc:  8253 /  8276 =  99.722
1, 0  acc:  2267 /  2874 =  78.880
1, 1  acc:    27 /   182 =  14.835
------------------------------------
Average acc: 18695 / 19867 =  94.101
Robust  acc:    27 /   182 =  14.835
------------------------------------
Save biased model at epoch 2
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch2_seed49.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 94.374
Robust Acc: 19.444 | Best Acc: 99.814
-------------------------------------
Training, Epoch 2:
Accuracies by groups:
0, 0  acc:  9447 /  9767 =  96.724
0, 1  acc:  7521 /  7535 =  99.814
1, 0  acc:  1836 /  2480 =  74.032
1, 1  acc:    35 /   180 =  19.444
------------------------------------
Average acc: 18839 / 19962 =  94.374
Robust  acc:    35 /   180 =  19.444
------------------------------------
Accuracies by groups:
0, 0  acc:  9447 /  9767 =  96.724
0, 1  acc:  7521 /  7535 =  99.814
1, 0  acc:  1836 /  2480 =  74.032
1, 1  acc:    35 /   180 =  19.444
------------------------------------
Average acc: 18839 / 19962 =  94.374
Robust  acc:    35 /   180 =  19.444
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9447 /  9767 =  96.724
0, 1  acc:  7521 /  7535 =  99.814
1, 0  acc:  1836 /  2480 =  74.032
1, 1  acc:    35 /   180 =  19.444
------------------------------------
Average acc: 18839 / 19962 =  94.374
Robust  acc:    35 /   180 =  19.444
------------------------------------
Epoch:   4 | Train Loss: 0.000 | Train Acc: 94.233 | Val Loss: 0.001 | Val Acc: 94.468
Training:
Accuracies by groups:
0, 0  acc: 68852 / 71629 =  96.123
0, 1  acc: 66622 / 66874 =  99.623
1, 0  acc: 17577 / 22880 =  76.823
1, 1  acc:   332 /  1387 =  23.937
--------------------------------------
Average acc: 153383 / 162770 =  94.233
Robust  acc:   332 /  1387 =  23.937
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8109 /  8535 =  95.009
0, 1  acc:  8248 /  8276 =  99.662
1, 0  acc:  2374 /  2874 =  82.603
1, 1  acc:    37 /   182 =  20.330
------------------------------------
Average acc: 18768 / 19867 =  94.468
Robust  acc:    37 /   182 =  20.330
------------------------------------
Save biased model at epoch 3
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch3_seed49.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 95.036
Robust Acc: 28.889 | Best Acc: 99.748
-------------------------------------
Training, Epoch 3:
Accuracies by groups:
0, 0  acc:  9429 /  9767 =  96.539
0, 1  acc:  7516 /  7535 =  99.748
1, 0  acc:  1974 /  2480 =  79.597
1, 1  acc:    52 /   180 =  28.889
------------------------------------
Average acc: 18971 / 19962 =  95.036
Robust  acc:    52 /   180 =  28.889
------------------------------------
Accuracies by groups:
0, 0  acc:  9429 /  9767 =  96.539
0, 1  acc:  7516 /  7535 =  99.748
1, 0  acc:  1974 /  2480 =  79.597
1, 1  acc:    52 /   180 =  28.889
------------------------------------
Average acc: 18971 / 19962 =  95.036
Robust  acc:    52 /   180 =  28.889
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9429 /  9767 =  96.539
0, 1  acc:  7516 /  7535 =  99.748
1, 0  acc:  1974 /  2480 =  79.597
1, 1  acc:    52 /   180 =  28.889
------------------------------------
Average acc: 18971 / 19962 =  95.036
Robust  acc:    52 /   180 =  28.889
------------------------------------
Epoch:   5 | Train Loss: 0.000 | Train Acc: 94.650 | Val Loss: 0.001 | Val Acc: 94.846
Training:
Accuracies by groups:
0, 0  acc: 68841 / 71629 =  96.108
0, 1  acc: 66557 / 66874 =  99.526
1, 0  acc: 18249 / 22880 =  79.760
1, 1  acc:   415 /  1387 =  29.921
--------------------------------------
Average acc: 154062 / 162770 =  94.650
Robust  acc:   415 /  1387 =  29.921
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8174 /  8535 =  95.770
0, 1  acc:  8252 /  8276 =  99.710
1, 0  acc:  2375 /  2874 =  82.637
1, 1  acc:    42 /   182 =  23.077
------------------------------------
Average acc: 18843 / 19867 =  94.846
Robust  acc:    42 /   182 =  23.077
------------------------------------
Save biased model at epoch 4
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch4_seed49.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 95.251
Robust Acc: 31.111 | Best Acc: 99.735
-------------------------------------
Training, Epoch 4:
Accuracies by groups:
0, 0  acc:  9457 /  9767 =  96.826
0, 1  acc:  7515 /  7535 =  99.735
1, 0  acc:  1986 /  2480 =  80.081
1, 1  acc:    56 /   180 =  31.111
------------------------------------
Average acc: 19014 / 19962 =  95.251
Robust  acc:    56 /   180 =  31.111
------------------------------------
Accuracies by groups:
0, 0  acc:  9457 /  9767 =  96.826
0, 1  acc:  7515 /  7535 =  99.735
1, 0  acc:  1986 /  2480 =  80.081
1, 1  acc:    56 /   180 =  31.111
------------------------------------
Average acc: 19014 / 19962 =  95.251
Robust  acc:    56 /   180 =  31.111
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9457 /  9767 =  96.826
0, 1  acc:  7515 /  7535 =  99.735
1, 0  acc:  1986 /  2480 =  80.081
1, 1  acc:    56 /   180 =  31.111
------------------------------------
Average acc: 19014 / 19962 =  95.251
Robust  acc:    56 /   180 =  31.111
------------------------------------
replace: True
Checkpoint saved at ./model/celebA/config/bias-end_seed49.pt
training biased model is done
