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/4e8b0d277dfc1f77d5969beb23791047
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 767499454
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	trial_seed: 0
	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: 0.7010166027828918
	lambda2: 0.6269010951324223
	last_k_epoch: 0.38851977780027735
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.131347198605345
	weight_decay: 1e-06
	worst_case_p: 0.3
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    
0.0159735420  0.0136787571  0.0113285273  0.0206185567  0.0140320733  0.0114547537  0.0118243243  0.0146561443  0.0183591509  0.0149253731  0.0000000000  9.5492725372  2.1706647873  0             1.5001630783 
0.6300933247  0.7750877404  0.6189495366  0.6412371134  0.8018327606  0.6827033219  0.8769707207  0.8331454340  0.8680436030  0.8094144661  4.9433573635  5.2512092876  2.4395728111  300           0.3011343153 
0.7125272062  0.8385742255  0.6972193615  0.7278350515  0.9034936999  0.7686139748  0.9529842342  0.8917700113  0.9520940906  0.8553386912  9.8867147271  2.7230798833  2.4395728111  600           0.2941728528 
0.7261824877  0.8473227850  0.7059732235  0.7463917526  0.9338487973  0.7754868270  0.9701576577  0.8996617813  0.9687320711  0.8668197474  14.830072090  2.0684883936  2.4395728111  900           0.2967155695 
0.7321074030  0.8556653024  0.7116374871  0.7525773196  0.9521764032  0.7857961054  0.9828265766  0.9109357384  0.9793459552  0.8702640643  19.773429454  1.7970941285  2.4395728111  1200          0.2941266918 
0.7377737901  0.8609851052  0.7188465499  0.7567010309  0.9604810997  0.7903780069  0.9856418919  0.9165727170  0.9825014343  0.8760045924  24.716786817  1.6358108723  2.4395728111  1500          0.2948241011 
0.7326191509  0.8568400338  0.7188465499  0.7463917526  0.9670675830  0.7961053837  0.9873310811  0.9052987599  0.9856569134  0.8691159587  29.660144181  1.5786948192  2.4395728111  1800          0.2879678734 
0.7331351457  0.8583570347  0.7178166838  0.7484536082  0.9733676976  0.7961053837  0.9915540541  0.9075535513  0.9888123924  0.8714121699  34.603501544  1.5035164976  2.4395728111  2100          0.3032493583 
0.7377737901  0.8705101340  0.7188465499  0.7567010309  0.9725085911  0.8098510882  0.9915540541  0.9210822999  0.9896729776  0.8805970149  39.546858908  1.4383418397  2.4395728111  2400          0.3005120269 
0.7406080453  0.8621485495  0.7203913491  0.7608247423  0.9756586483  0.8064146621  0.9940878378  0.9120631342  0.9911072863  0.8679678530  44.490216271  1.4010542965  2.4395728111  2700          0.2996598585 
0.7393196510  0.8690000365  0.7198764161  0.7587628866  0.9773768614  0.8098510882  0.9954954955  0.9177001127  0.9902467011  0.8794489093  49.433573635  1.3549483860  2.4395728111  3000          0.2953736997 
0.7377727284  0.8686156918  0.7209062822  0.7546391753  0.9833906071  0.8029782360  0.9926801802  0.9188275085  0.9919678715  0.8840413318  54.376930999  1.1521123282  5.3998112679  3300          0.3024812325 
0.7357108727  0.8571787963  0.7209062822  0.7505154639  0.9802405498  0.7903780069  0.9949324324  0.9131905299  0.9922547332  0.8679678530  59.320288362  0.9959352684  5.3998112679  3600          0.3068107231 
0.7359683392  0.8648197933  0.7214212152  0.7505154639  0.9793814433  0.7983963345  0.9952139640  0.9143179256  0.9945496271  0.8817451206  64.263645726  0.9447164432  5.3998112679  3900          0.3141405185 
0.7333915505  0.8689596041  0.7203913491  0.7463917526  0.9822451317  0.7995418099  0.9932432432  0.9255918828  0.9951233505  0.8817451206  69.207003089  0.9006661330  5.3998112679  4200          0.3132222088 
0.7326180892  0.8666987861  0.7209062822  0.7443298969  0.9816723940  0.7983963345  0.9926801802  0.9199549042  0.9951233505  0.8817451206  74.150360453  0.8714852395  5.3998112679  4500          0.2953027527 
0.7287529061  0.8617633281  0.7193614830  0.7381443299  0.9822451317  0.8006872852  0.9963400901  0.9131905299  0.9951233505  0.8714121699  79.093717816  0.8484086641  5.3998112679  4800          0.2994010218 
0.7290103726  0.8587328333  0.7198764161  0.7381443299  0.9822451317  0.7961053837  0.9960585586  0.9086809470  0.9954102123  0.8714121699  82.389289392  0.8270776838  5.3998112679  5000          0.3016784239 
