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: [2]
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: 3
	output_dir: sweep/ablation3/outputs/28d90a056bc95f00a2dfdbdb9a28a22e
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 2132709150
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	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: 0.8610090196552951
	lambda2: 0.5777772877463595
	last_k_epoch: 0.32350558703299503
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.866557071912062
	weight_decay: 0.0001
	worst_case_p: 0.25
using augment transform
using augment transform
using normal 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    
0.2594273028  0.1069830094  0.0424028269  0.0282685512  0.0607058824  0.0941619586  0.2627570449  0.2560975610  0.1736393928  0.1985185185  0.0000000000  5.0533313751  2.0073552132  0             1.9333505630 
0.7937185366  0.8627267260  1.0000000000  0.9964664311  0.7727058824  0.7250470810  0.7825590251  0.8048780488  0.9233617179  0.8666666667  8.4805653710  1.9309389075  2.2578248978  300           0.6439959613 
0.8089543120  0.8696463692  1.0000000000  1.0000000000  0.7943529412  0.7363465160  0.8038842346  0.8140243902  0.9526101444  0.8725925926  16.961130742  1.3316746430  2.2578248978  600           0.6579877257 
0.8110539767  0.8652377115  1.0000000000  0.9964664311  0.8098823529  0.7325800377  0.7943640518  0.8277439024  0.9618659756  0.8666666667  25.441696113  1.2181635803  2.2578248978  900           0.6471294586 
0.8076243889  0.8680667553  1.0000000000  0.9964664311  0.8348235294  0.7306967985  0.7936024372  0.8216463415  0.9729729730  0.8770370370  33.922261484  1.1081673014  2.2578248978  1200          0.6458556469 
0.8036212682  0.8659217407  1.0000000000  1.0000000000  0.8550588235  0.7325800377  0.7977913176  0.8094512195  0.9792669382  0.8651851852  42.402826855  1.0364283309  2.2578248978  1500          0.6458529147 
0.8001910999  0.8710357813  1.0000000000  1.0000000000  0.8677647059  0.7419962335  0.7985529322  0.8018292683  0.9818585709  0.8711111111  50.883392226  1.0120521802  2.2578248978  1800          0.6402048659 
0.8017149096  0.8653153480  1.0000000000  0.9929328622  0.8823529412  0.7363465160  0.8000761615  0.8033536585  0.9840799704  0.8666666667  59.363957597  0.9918040609  2.2578248978  2100          0.6384391268 
0.8005724877  0.8741745132  1.0000000000  1.0000000000  0.8851764706  0.7514124294  0.7977913176  0.8033536585  0.9892632358  0.8711111111  67.844522968  0.9644481256  2.2578248978  2400          0.6445532473 
0.7984768865  0.8683764435  1.0000000000  0.9964664311  0.9054117647  0.7419962335  0.7966488957  0.8003048780  0.9892632358  0.8666666667  76.325088339  0.9866871885  2.2578248978  2700          0.6492166996 
0.7980966596  0.8706758733  1.0000000000  1.0000000000  0.9082352941  0.7438794727  0.7943640518  0.8018292683  0.9900037023  0.8681481481  84.805653710  1.0095536774  2.2578248978  3000          0.6384414053 
0.7977158523  0.8696319363  1.0000000000  0.9964664311  0.9176470588  0.7457627119  0.7936024372  0.8018292683  0.9925953351  0.8666666667  93.286219081  0.9701918405  2.2578248978  3300          0.6584938240 
0.7960010584  0.8653716308  1.0000000000  0.9964664311  0.9242352941  0.7344632768  0.7932216299  0.7987804878  0.9914846353  0.8651851852  101.76678445  0.6052290954  5.3945398331  3600          0.6555637701 
0.7965728499  0.8683908765  1.0000000000  1.0000000000  0.9294117647  0.7325800377  0.7928408225  0.8003048780  0.9900037023  0.8725925926  110.24734982  0.4304202873  5.3945398331  3900          0.6380140980 
0.7950490402  0.8674450719  1.0000000000  1.0000000000  0.9280000000  0.7401129944  0.7913175933  0.7987804878  0.9933358016  0.8622222222  118.72791519  0.4125134167  5.3945398331  4200          0.6356035733 
0.7937156341  0.8711552675  1.0000000000  0.9964664311  0.9360000000  0.7532956685  0.7901751714  0.7972560976  0.9933358016  0.8637037037  127.20848056  0.3989667974  5.3945398331  4500          0.6401391586 
0.7931438426  0.8697240057  1.0000000000  0.9964664311  0.9350588235  0.7401129944  0.7905559787  0.7957317073  0.9944465013  0.8725925926  135.68904593  0.3944043188  5.3945398331  4800          0.6409027863 
0.7946676523  0.8751621675  1.0000000000  1.0000000000  0.9454117647  0.7514124294  0.7920792079  0.7972560976  0.9940762680  0.8740740741  141.34275618  0.3860167155  5.3945398331  5000          0.6410148120 
