Environment:
	Python: 3.10.11
	PyTorch: 2.0.1
	Torchvision: 0.15.2
	CUDA: 11.7
	CUDNN: 8500
	NumPy: 1.24.3
	PIL: 9.4.0
	Testing environment: [1]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: VLCS
	holdout_fraction: 0.2
	hparams: {
    "resnet18": false,
    "resnet_dropout": 0,
    "nonlinear_classifier": false,
    "data_augmentation": true,
    "clip_backbone": "ViT-B/32",
    "student_model": "resnet",
    "SMA": true,
    "batch_size": 32
}
	hparams_seed: 0
	output_dir: sweep/ablation3/outputs/75d99b01ece3341092d058fb8cbb08e9
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 2105976066
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	trial_seed: 2
	uda_holdout_fraction: 0
	visualize: False
Not saving models
HParams:
	SMA: True
	batch_size: 32
	class_balanced: False
	clip_backbone: ViT-B/32
	data_augmentation: True
	lambda1: 0.5
	lambda2: 0.5
	last_k_epoch: 0.25
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3
	weight_decay: 0.0
	worst_case_p: 0.3333333333333333
using augment transform
using normal transform
using augment transform
using augment transform
using device:  cuda
Using ViT-B/32...
constructing student model
using resnet 50
Using SMA
n_steps 5001
checkpoint_freq 300
agg_test_acc  agg_val_acc   env0_in_acc   env0_out_acc  env1_in_acc   env1_out_acc  env2_in_acc   env2_out_acc  env3_in_acc   env3_out_acc  epoch         loss          mem_gb        step          step_time    
0.0477771131  0.1071905520  0.0848056537  0.1060070671  0.0428235294  0.0527306968  0.0818735720  0.0792682927  0.1451314328  0.1362962963  0.0000000000  4.3867287636  2.3337798119  0             1.6622796059 
0.6766314387  0.9005191742  1.0000000000  0.9929328622  0.6696470588  0.6836158192  0.8846153846  0.8064024390  0.9326175491  0.9022222222  8.4805653710  1.3166940055  2.5977830887  300           0.1677367171 
0.6688654035  0.9126284786  1.0000000000  0.9929328622  0.6597647059  0.6779661017  0.9325971059  0.8338414634  0.9548315439  0.9111111111  16.961130742  0.8179677681  2.5977830887  600           0.1882512442 
0.6627464271  0.9140108398  1.0000000000  1.0000000000  0.6531764706  0.6723163842  0.9543031226  0.8353658537  0.9648278415  0.9066666667  25.441696113  0.6973689851  2.5977830887  900           0.1913338439 
0.6613346623  0.9128329835  1.0000000000  0.9964664311  0.6503529412  0.6723163842  0.9664889566  0.8353658537  0.9770455387  0.9066666667  33.922261484  0.6475508114  2.5977830887  1200          0.1891923356 
0.6632179015  0.9100888284  1.0000000000  1.0000000000  0.6503529412  0.6760828625  0.9760091394  0.8384146341  0.9837097371  0.8918518519  42.402826855  0.6156170721  2.5977830887  1500          0.1890154894 
0.6580392154  0.9103066360  1.0000000000  0.9964664311  0.6494117647  0.6666666667  0.9824828637  0.8292682927  0.9881525361  0.9051851852  50.883392226  0.5971506446  2.5977830887  1800          0.1880399942 
0.6575686271  0.9096655156  1.0000000000  0.9929328622  0.6484705882  0.6666666667  0.9862909368  0.8338414634  0.9900037023  0.9022222222  59.363957597  0.5742105974  2.5977830887  2100          0.1847509090 
0.6580396585  0.9167979037  1.0000000000  0.9964664311  0.6475294118  0.6685499058  0.9900990099  0.8368902439  0.9907441688  0.9170370370  67.844522968  0.5773765750  2.5977830887  2400          0.1872093344 
0.6587459839  0.9137305563  1.0000000000  0.9929328622  0.6470588235  0.6704331450  0.9900990099  0.8460365854  0.9922251018  0.9022222222  76.325088339  0.5537398404  2.5977830887  2700          0.1865390484 
0.6585106898  0.9081554283  1.0000000000  0.9929328622  0.6465882353  0.6704331450  0.9954303123  0.8307926829  0.9929655683  0.9007407407  84.805653710  0.5555343234  2.5977830887  3000          0.1887482572 
0.6599233408  0.9101593428  1.0000000000  0.9929328622  0.6456470588  0.6741996234  0.9958111196  0.8338414634  0.9962976675  0.9037037037  93.286219081  0.5395456570  2.5977830887  3300          0.1864499656 
0.6582758388  0.9128615893  1.0000000000  0.9964664311  0.6442352941  0.6723163842  0.9950495050  0.8384146341  0.9951869678  0.9037037037  101.76678445  0.5472746357  2.5977830887  3600          0.1870488946 
0.6573342192  0.9113085933  1.0000000000  0.9964664311  0.6442352941  0.6704331450  0.9958111196  0.8307926829  0.9962976675  0.9066666667  110.24734982  0.4468101718  5.3947153091  3900          0.2067218367 
0.6594523094  0.9103352419  1.0000000000  0.9964664311  0.6465882353  0.6723163842  0.9984767708  0.8323170732  0.9981488338  0.9022222222  118.72791519  0.3066147809  5.3947153091  4200          0.2213737583 
0.6615703996  0.9139822340  1.0000000000  1.0000000000  0.6489411765  0.6741996234  0.9980959634  0.8323170732  0.9981488338  0.9096296296  127.20848056  0.2931486206  5.3947153091  4500          0.2226507592 
0.6610998113  0.9144431913  1.0000000000  0.9964664311  0.6480000000  0.6741996234  0.9977151561  0.8490853659  0.9974083673  0.8977777778  135.68904593  0.2850482013  5.3947153091  4800          0.2222407571 
0.6613351055  0.9102923331  1.0000000000  0.9964664311  0.6484705882  0.6741996234  0.9980959634  0.8277439024  0.9977786005  0.9066666667  141.34275618  0.2811155956  5.3947153091  5000          0.2239846468 
