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: [0]
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: 4
	output_dir: sweep/ablation3/outputs/0c80661391cb1f0ab8cf9c4e6a2f0c97
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1530427239
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	trial_seed: 1
	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: 0.6171767606394463
	lambda2: 0.5293911814442921
	last_k_epoch: 0.3102645027326114
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.022572617872769
	weight_decay: 0.0001
	worst_case_p: 0.2
using normal transform
using augment 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    
0.1696113073  0.2396986561  0.1766784452  0.1625441696  0.2216470588  0.2278719397  0.2875095202  0.2408536585  0.2265827471  0.2503703704  0.0000000000  3.2749364376  1.7945408821  0             1.6064624786 
0.9792402822  0.7902132166  0.9796819788  0.9787985866  0.7529411765  0.7363465160  0.8233054075  0.7972560976  0.8937430581  0.8370370370  8.4805653710  1.7757212762  2.0945272446  300           0.6262400969 
0.9889575967  0.8071136295  0.9885159011  0.9893992933  0.7783529412  0.7269303202  0.8895658797  0.8277439024  0.9303961496  0.8666666667  16.961130742  1.4204017405  2.0945272446  600           0.6424110595 
0.9902826850  0.8124881976  0.9876325088  0.9929328622  0.8160000000  0.7532956685  0.9116527037  0.8323170732  0.9485375787  0.8518518519  25.441696113  1.3153796101  2.0945272446  900           0.6350571418 
0.9898409889  0.8141691799  0.9867491166  0.9929328622  0.8329411765  0.7344632768  0.9341203351  0.8384146341  0.9559422436  0.8696296296  33.922261484  1.2830245463  2.0945272446  1200          0.6274918127 
0.9889575967  0.8192769686  0.9849823322  0.9929328622  0.8385882353  0.7495291902  0.9459253618  0.8475609756  0.9744539060  0.8607407407  42.402826855  1.1906199749  2.0945272446  1500          0.6495942577 
0.9885159006  0.8201358966  0.9840989399  0.9929328622  0.8489411765  0.7495291902  0.9607768469  0.8338414634  0.9822288041  0.8770370370  50.883392226  1.1230683599  2.0945272446  1800          0.6238003302 
0.9845406356  0.8153336622  0.9796819788  0.9893992933  0.8649411765  0.7363465160  0.9702970297  0.8429878049  0.9855609034  0.8666666667  59.363957597  1.0397436611  2.0945272446  2100          0.6413089267 
0.9854240278  0.8240802619  0.9814487633  0.9893992933  0.8672941176  0.7551789077  0.9790555979  0.8429878049  0.9866716031  0.8740740741  67.844522968  0.9705695780  2.0945272446  2400          0.6277206866 
0.9845406356  0.8206102279  0.9832155477  0.9858657244  0.8861176471  0.7476459510  0.9824828637  0.8460365854  0.9918548686  0.8681481481  76.325088339  0.9627952558  2.0945272446  2700          0.6333246096 
0.9845406356  0.8183670808  0.9832155477  0.9858657244  0.9007058824  0.7438794727  0.9847677075  0.8460365854  0.9933358016  0.8651851852  84.805653710  0.9400556912  2.0945272446  3000          0.6358534042 
0.9845406356  0.8236150406  0.9832155477  0.9858657244  0.9138823529  0.7551789077  0.9900990099  0.8460365854  0.9948167345  0.8696296296  93.286219081  0.9368798401  2.0945272446  3300          0.6298728140 
0.9840989394  0.8199681786  0.9823321555  0.9858657244  0.9209411765  0.7457627119  0.9916222391  0.8445121951  0.9948167345  0.8696296296  101.76678445  0.7291224800  5.4004793167  3600          0.6247760479 
0.9858657239  0.8197421899  0.9823321555  0.9893992933  0.9284705882  0.7495291902  0.9939070830  0.8445121951  0.9966679008  0.8651851852  110.24734982  0.4976346558  5.4004793167  3900          0.6123160815 
0.9863074200  0.8217450454  0.9832155477  0.9893992933  0.9336470588  0.7570621469  0.9939070830  0.8429878049  0.9977786005  0.8651851852  118.72791519  0.4798359836  5.4004793167  4200          0.6108557749 
0.9863074200  0.8194722334  0.9832155477  0.9893992933  0.9458823529  0.7608286252  0.9927646611  0.8353658537  0.9959274343  0.8622222222  127.20848056  0.4703024639  5.4004793167  4500          0.6139407746 
0.9863074200  0.8221203152  0.9832155477  0.9893992933  0.9538823529  0.7476459510  0.9961919269  0.8490853659  0.9981488338  0.8696296296  135.68904593  0.4665262527  5.4004793167  4800          0.6063268224 
0.9867491161  0.8192626657  0.9840989399  0.9893992933  0.9430588235  0.7495291902  0.9980959634  0.8460365854  0.9966679008  0.8622222222  141.34275618  0.4566429704  5.4004793167  5000          0.6163940609 
