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: 22
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=22-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: 84.807 | Val Loss: 0.003 | Val Acc: 84.618
Training:
Accuracies by groups:
0, 0  acc: 71331 / 71629 =  99.584
0, 1  acc: 66587 / 66874 =  99.571
1, 0  acc:   119 / 22880 =   0.520
1, 1  acc:     4 /  1387 =   0.288
--------------------------------------
Average acc: 138041 / 162770 =  84.807
Robust  acc:     4 /  1387 =   0.288
--------------------------------------
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_seed22.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_seed22.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: 87.827 | Val Loss: 0.001 | Val Acc: 92.253
Training:
Accuracies by groups:
0, 0  acc: 71077 / 71629 =  99.229
0, 1  acc: 66868 / 66874 =  99.991
1, 0  acc:  4989 / 22880 =  21.805
1, 1  acc:    22 /  1387 =   1.586
--------------------------------------
Average acc: 142956 / 162770 =  87.827
Robust  acc:    22 /  1387 =   1.586
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8232 /  8535 =  96.450
0, 1  acc:  8275 /  8276 =  99.988
1, 0  acc:  1813 /  2874 =  63.083
1, 1  acc:     8 /   182 =   4.396
------------------------------------
Average acc: 18328 / 19867 =  92.253
Robust  acc:     8 /   182 =   4.396
------------------------------------
Save biased model at epoch 1
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch1_seed22.pt
New max average-worst acc gap: 87.85788128416608
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_seed22.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 92.706
Robust Acc: 7.222 | Best Acc: 99.987
------------------------------------
Training, Epoch 1:
Accuracies by groups:
0, 0  acc:  9547 /  9767 =  97.748
0, 1  acc:  7534 /  7535 =  99.987
1, 0  acc:  1412 /  2480 =  56.935
1, 1  acc:    13 /   180 =   7.222
------------------------------------
Average acc: 18506 / 19962 =  92.706
Robust  acc:    13 /   180 =   7.222
------------------------------------
Accuracies by groups:
0, 0  acc:  9547 /  9767 =  97.748
0, 1  acc:  7534 /  7535 =  99.987
1, 0  acc:  1412 /  2480 =  56.935
1, 1  acc:    13 /   180 =   7.222
------------------------------------
Average acc: 18506 / 19962 =  92.706
Robust  acc:    13 /   180 =   7.222
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9547 /  9767 =  97.748
0, 1  acc:  7534 /  7535 =  99.987
1, 0  acc:  1412 /  2480 =  56.935
1, 1  acc:    13 /   180 =   7.222
------------------------------------
Average acc: 18506 / 19962 =  92.706
Robust  acc:    13 /   180 =   7.222
------------------------------------
Epoch:   3 | Train Loss: 0.000 | Train Acc: 93.180 | Val Loss: 0.001 | Val Acc: 94.020
Training:
Accuracies by groups:
0, 0  acc: 69143 / 71629 =  96.529
0, 1  acc: 66751 / 66874 =  99.816
1, 0  acc: 15587 / 22880 =  68.125
1, 1  acc:   188 /  1387 =  13.554
--------------------------------------
Average acc: 151669 / 162770 =  93.180
Robust  acc:   188 /  1387 =  13.554
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8108 /  8535 =  94.997
0, 1  acc:  8255 /  8276 =  99.746
1, 0  acc:  2288 /  2874 =  79.610
1, 1  acc:    28 /   182 =  15.385
------------------------------------
Average acc: 18679 / 19867 =  94.020
Robust  acc:    28 /   182 =  15.385
------------------------------------
Save biased model at epoch 2
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch2_seed22.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 94.344
Robust Acc: 17.778 | Best Acc: 99.827
-------------------------------------
Training, Epoch 2:
Accuracies by groups:
0, 0  acc:  9418 /  9767 =  96.427
0, 1  acc:  7522 /  7535 =  99.827
1, 0  acc:  1861 /  2480 =  75.040
1, 1  acc:    32 /   180 =  17.778
------------------------------------
Average acc: 18833 / 19962 =  94.344
Robust  acc:    32 /   180 =  17.778
------------------------------------
Accuracies by groups:
0, 0  acc:  9418 /  9767 =  96.427
0, 1  acc:  7522 /  7535 =  99.827
1, 0  acc:  1861 /  2480 =  75.040
1, 1  acc:    32 /   180 =  17.778
------------------------------------
Average acc: 18833 / 19962 =  94.344
Robust  acc:    32 /   180 =  17.778
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9418 /  9767 =  96.427
0, 1  acc:  7522 /  7535 =  99.827
1, 0  acc:  1861 /  2480 =  75.040
1, 1  acc:    32 /   180 =  17.778
------------------------------------
Average acc: 18833 / 19962 =  94.344
Robust  acc:    32 /   180 =  17.778
------------------------------------
Epoch:   4 | Train Loss: 0.000 | Train Acc: 94.157 | Val Loss: 0.001 | Val Acc: 94.468
Training:
Accuracies by groups:
0, 0  acc: 68883 / 71629 =  96.166
0, 1  acc: 66633 / 66874 =  99.640
1, 0  acc: 17437 / 22880 =  76.211
1, 1  acc:   307 /  1387 =  22.134
--------------------------------------
Average acc: 153260 / 162770 =  94.157
Robust  acc:   307 /  1387 =  22.134
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8170 /  8535 =  95.723
0, 1  acc:  8256 /  8276 =  99.758
1, 0  acc:  2310 /  2874 =  80.376
1, 1  acc:    32 /   182 =  17.582
------------------------------------
Average acc: 18768 / 19867 =  94.468
Robust  acc:    32 /   182 =  17.582
------------------------------------
Save biased model at epoch 3
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch3_seed22.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 94.865
Robust Acc: 23.333 | Best Acc: 99.761
-------------------------------------
Training, Epoch 3:
Accuracies by groups:
0, 0  acc:  9475 /  9767 =  97.010
0, 1  acc:  7517 /  7535 =  99.761
1, 0  acc:  1903 /  2480 =  76.734
1, 1  acc:    42 /   180 =  23.333
------------------------------------
Average acc: 18937 / 19962 =  94.865
Robust  acc:    42 /   180 =  23.333
------------------------------------
Accuracies by groups:
0, 0  acc:  9475 /  9767 =  97.010
0, 1  acc:  7517 /  7535 =  99.761
1, 0  acc:  1903 /  2480 =  76.734
1, 1  acc:    42 /   180 =  23.333
------------------------------------
Average acc: 18937 / 19962 =  94.865
Robust  acc:    42 /   180 =  23.333
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9475 /  9767 =  97.010
0, 1  acc:  7517 /  7535 =  99.761
1, 0  acc:  1903 /  2480 =  76.734
1, 1  acc:    42 /   180 =  23.333
------------------------------------
Average acc: 18937 / 19962 =  94.865
Robust  acc:    42 /   180 =  23.333
------------------------------------
Epoch:   5 | Train Loss: 0.000 | Train Acc: 94.609 | Val Loss: 0.001 | Val Acc: 94.730
Training:
Accuracies by groups:
0, 0  acc: 68841 / 71629 =  96.108
0, 1  acc: 66583 / 66874 =  99.565
1, 0  acc: 18193 / 22880 =  79.515
1, 1  acc:   378 /  1387 =  27.253
--------------------------------------
Average acc: 153995 / 162770 =  94.609
Robust  acc:   378 /  1387 =  27.253
--------------------------------------
Validating:
Accuracies by groups:
0, 0  acc:  8204 /  8535 =  96.122
0, 1  acc:  8257 /  8276 =  99.770
1, 0  acc:  2324 /  2874 =  80.863
1, 1  acc:    35 /   182 =  19.231
------------------------------------
Average acc: 18820 / 19867 =  94.730
Robust  acc:    35 /   182 =  19.231
------------------------------------
Save biased model at epoch 4
replace: True
Checkpoint saved at ./model/celebA/config/stage_one_erm_model_b_epoch4_seed22.pt
-------------------------------------------
Avg Test Loss: 0.001 | Avg Test Acc: 95.186
Robust Acc: 25.556 | Best Acc: 99.761
-------------------------------------
Training, Epoch 4:
Accuracies by groups:
0, 0  acc:  9501 /  9767 =  97.277
0, 1  acc:  7517 /  7535 =  99.761
1, 0  acc:  1937 /  2480 =  78.105
1, 1  acc:    46 /   180 =  25.556
------------------------------------
Average acc: 19001 / 19962 =  95.186
Robust  acc:    46 /   180 =  25.556
------------------------------------
Accuracies by groups:
0, 0  acc:  9501 /  9767 =  97.277
0, 1  acc:  7517 /  7535 =  99.761
1, 0  acc:  1937 /  2480 =  78.105
1, 1  acc:    46 /   180 =  25.556
------------------------------------
Average acc: 19001 / 19962 =  95.186
Robust  acc:    46 /   180 =  25.556
------------------------------------
Testing:
Accuracies by groups:
0, 0  acc:  9501 /  9767 =  97.277
0, 1  acc:  7517 /  7535 =  99.761
1, 0  acc:  1937 /  2480 =  78.105
1, 1  acc:    46 /   180 =  25.556
------------------------------------
Average acc: 19001 / 19962 =  95.186
Robust  acc:    46 /   180 =  25.556
------------------------------------
replace: True
Checkpoint saved at ./model/celebA/config/bias-end_seed22.pt
training biased model is done
