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: 3
	output_dir: sweep/ablation3/outputs/1f94e7aceb5607db13f59ca1f8bb6a38
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 2147007459
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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: 0.5694511041907044
	lambda2: 0.6621108818243455
	last_k_epoch: 0.20248994529588413
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.502579147595572
	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    
0.0108167794  0.0194079981  0.0154479918  0.0061855670  0.0194730813  0.0171821306  0.0191441441  0.0157835400  0.0163511188  0.0252583238  0.0000000000  7.8561158180  1.7954735756  0             1.4749815464 
0.5569250531  0.7332619593  0.5653964985  0.5484536082  0.7511454754  0.6437571592  0.8417792793  0.7936865840  0.8141135972  0.7623421355  4.9433573635  5.2834934831  2.0943040848  300           0.3029563435 
0.6651162047  0.8275492879  0.6745623069  0.6556701031  0.8960481100  0.7628865979  0.9498873874  0.8804960541  0.9383247275  0.8392652124  9.8867147271  3.0496792841  2.0943040848  600           0.2927290916 
0.6944907468  0.8469527915  0.6879505664  0.7010309278  0.9327033219  0.7949599084  0.9701576577  0.8951521984  0.9647160069  0.8507462687  14.830072090  2.2305697294  2.0943040848  900           0.2907349006 
0.7104653505  0.8449919465  0.6972193615  0.7237113402  0.9533218786  0.7846506300  0.9819819820  0.9041713641  0.9787722318  0.8461538462  19.773429454  1.8344719787  2.0943040848  1200          0.2989520391 
0.7181957167  0.8553239097  0.7003089598  0.7360824742  0.9644902635  0.7949599084  0.9845157658  0.9030439684  0.9853700516  0.8679678530  24.716786817  1.5655628943  2.0943040848  1500          0.2866890653 
0.7261835494  0.8591319720  0.7039134912  0.7484536082  0.9733676976  0.7926689576  0.9887387387  0.9064261556  0.9902467011  0.8783008037  29.660144181  1.4451163912  2.0943040848  1800          0.2940741865 
0.7308179469  0.8632613725  0.7131822863  0.7484536082  0.9756586483  0.7983963345  0.9932432432  0.9188275085  0.9934021801  0.8725602755  34.603501544  1.3252914834  2.0943040848  2100          0.2892349211 
0.7290114343  0.8609823642  0.7178166838  0.7402061856  0.9785223368  0.8029782360  0.9946509009  0.9154453213  0.9934021801  0.8645235362  39.546858908  1.2538388654  2.0943040848  2400          0.2893493835 
0.7282379730  0.8655765402  0.7183316169  0.7381443299  0.9810996564  0.8006872852  0.9932432432  0.9154453213  0.9925415950  0.8805970149  44.490216271  1.2335124928  2.0943040848  2700          0.3093937635 
0.7315860996  0.8648059866  0.7229660144  0.7402061856  0.9848224513  0.7983963345  0.9952139640  0.9165727170  0.9951233505  0.8794489093  49.433573635  1.1673997994  2.0943040848  3000          0.2946903785 
0.7331330222  0.8605928697  0.7219361483  0.7443298969  0.9816723940  0.7938144330  0.9969031532  0.9177001127  0.9965576592  0.8702640643  54.376930999  1.1331589214  2.0943040848  3300          0.2987931387 
0.7377706049  0.8678002114  0.7250257467  0.7505154639  0.9831042383  0.8052691867  0.9940878378  0.9267192785  0.9971313827  0.8714121699  59.320288362  1.1529317643  2.0943040848  3600          0.2929016463 
0.7416357880  0.8663159735  0.7265705458  0.7567010309  0.9833906071  0.8075601375  0.9954954955  0.9188275085  0.9977051061  0.8725602755  64.263645726  1.0575939886  2.0943040848  3900          0.2974004722 
0.7442115150  0.8686396873  0.7296601442  0.7587628866  0.9848224513  0.8167239404  0.9960585586  0.9131905299  0.9968445209  0.8760045924  69.207003089  0.9673085296  5.4025750160  4200          0.3118650293 
0.7416347263  0.8632561120  0.7286302781  0.7546391753  0.9848224513  0.8052691867  0.9963400901  0.9188275085  0.9974182444  0.8656716418  74.150360453  0.8333507224  5.4025750160  4500          0.2915191158 
0.7442115150  0.8647938228  0.7296601442  0.7587628866  0.9885452463  0.8052691867  0.9952139640  0.9177001127  0.9971313827  0.8714121699  79.093717816  0.7835012378  5.4025750160  4800          0.3022826568 
0.7452424429  0.8636646736  0.7296601442  0.7608247423  0.9868270332  0.8075601375  0.9960585586  0.9143179256  0.9971313827  0.8691159587  82.389289392  0.7529307777  5.4025750160  5000          0.3171226943 
