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: OfficeHome
	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/9316e00ae9f6105981c476f892582f09
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 693595898
	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    
0.0193206069  0.0095035529  0.0180226571  0.0206185567  0.0120274914  0.0114547537  0.0112612613  0.0090191657  0.0123350545  0.0080367394  0.0000000000  8.3313913345  1.7954735756  0             1.5504302979 
0.6094885703  0.7144125313  0.5921730175  0.6268041237  0.7279495991  0.6403207331  0.8054617117  0.7474633596  0.8057946070  0.7554535017  4.9433573635  5.8357908503  2.0943040848  300           0.3058392962 
0.6769798376  0.8192886226  0.6591143151  0.6948453608  0.8843069874  0.7628865979  0.9366554054  0.8545659526  0.9271371199  0.8404133180  9.8867147271  3.2423448237  2.0943040848  600           0.3165004126 
0.7117569300  0.8458788687  0.6915550978  0.7319587629  0.9241122566  0.7972508591  0.9634009009  0.8827508455  0.9563970166  0.8576349024  14.830072090  2.4001366536  2.0943040848  900           0.3149435941 
0.7251515598  0.8530750341  0.7059732235  0.7443298969  0.9498854525  0.8052691867  0.9771959459  0.8940248027  0.9736087206  0.8599311137  19.773429454  1.9165608899  2.0943040848  1200          0.3103655322 
0.7344256635  0.8602807330  0.7142121524  0.7546391753  0.9644902635  0.8098510882  0.9831081081  0.9041713641  0.9816408491  0.8668197474  24.716786817  1.6961100670  2.0943040848  1500          0.3008853753 
0.7395781792  0.8626044467  0.7183316169  0.7608247423  0.9659221077  0.8190148912  0.9890202703  0.8985343856  0.9859437751  0.8702640643  29.660144181  1.5625395091  2.0943040848  1800          0.3105814274 
0.7442157619  0.8701841907  0.7214212152  0.7670103093  0.9739404353  0.8258877434  0.9907094595  0.9098083427  0.9893861159  0.8748564868  34.603501544  1.4856357654  2.0943040848  2100          0.3042073226 
0.7442136385  0.8728234375  0.7255406797  0.7628865979  0.9745131730  0.8235967927  0.9898648649  0.9165727170  0.9896729776  0.8783008037  39.546858908  1.4568439098  2.0943040848  2400          0.3064264639 
0.7483373498  0.8690438651  0.7255406797  0.7711340206  0.9782359679  0.8247422680  0.9929617117  0.9086809470  0.9905335628  0.8737083812  44.490216271  1.4112595530  2.0943040848  2700          0.3018557644 
0.7488522828  0.8751204148  0.7265705458  0.7711340206  0.9788087056  0.8316151203  0.9940878378  0.9154453213  0.9928284567  0.8783008037  49.433573635  1.3649233667  2.0943040848  3000          0.3244987456 
0.7488522828  0.8774260489  0.7265705458  0.7711340206  0.9810996564  0.8373424971  0.9935247748  0.9131905299  0.9942627653  0.8817451206  54.376930999  1.3380240309  2.0943040848  3300          0.2995765424 
0.7524589377  0.8724786484  0.7296601442  0.7752577320  0.9831042383  0.8281786942  0.9926801802  0.9098083427  0.9925415950  0.8794489093  59.320288362  1.1665503597  5.4016079903  3600          0.3131665436 
0.7501396155  0.8731689926  0.7291452111  0.7711340206  0.9816723940  0.8270332188  0.9949324324  0.9222096956  0.9956970740  0.8702640643  64.263645726  0.9094309189  5.4016079903  3900          0.3042250164 
0.7496246824  0.8766202128  0.7281153450  0.7711340206  0.9825315006  0.8270332188  0.9926801802  0.9210822999  0.9945496271  0.8817451206  69.207003089  0.8524768492  5.4016079903  4200          0.3080906272 
0.7503981437  0.8807850066  0.7276004119  0.7731958763  0.9842497136  0.8316151203  0.9946509009  0.9278466742  0.9959839357  0.8828932262  74.150360453  0.8130173177  5.4016079903  4500          0.3038937887 
0.7493672159  0.8785215583  0.7276004119  0.7711340206  0.9831042383  0.8339060710  0.9943693694  0.9222096956  0.9939759036  0.8794489093  79.093717816  0.7792986433  5.4016079903  4800          0.3143278861 
0.7485948163  0.8750782289  0.7260556128  0.7711340206  0.9836769759  0.8235967927  0.9952139640  0.9233370913  0.9942627653  0.8783008037  82.389289392  0.7656676289  5.4016079903  5000          0.3007147753 
