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: [1]
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: 2
	output_dir: sweep/ablation3/outputs/44c368e4e181438063c6d2f6a0fe5416
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 843332380
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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: 0.7419102898692578
	lambda2: 0.5215383105176172
	last_k_epoch: 0.23762453204831346
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.9748462276330736
	weight_decay: 1e-06
	worst_case_p: 0.3
using augment transform
using normal 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    
0.0229095074  0.0138417867  0.0185375901  0.0164948454  0.0263459336  0.0194730813  0.0163288288  0.0124013529  0.0137693632  0.0126291619  0.0000000000  9.4504394531  2.1706647873  0             1.5239939690 
0.5073024052  0.8136348750  0.8861997940  0.7938144330  0.5105956472  0.5040091638  0.8969594595  0.8365276212  0.8772231784  0.8105625718  4.9433573635  5.3041985297  2.4395728111  300           0.2882253766 
0.5441008016  0.8441944544  0.9665293512  0.7979381443  0.5589919817  0.5292096220  0.9574887387  0.8827508455  0.9452094091  0.8518943743  9.8867147271  2.5203538815  2.4395728111  600           0.2908891431 
0.5498281784  0.8625803405  0.9783728115  0.8144329897  0.5658648339  0.5337915235  0.9693130631  0.9030439684  0.9609868044  0.8702640643  14.830072090  1.9085159210  2.4395728111  900           0.2895848298 
0.5545532643  0.8660800911  0.9876416066  0.8329896907  0.5695876289  0.5395189003  0.9786036036  0.9041713641  0.9713138267  0.8610792193  19.773429454  1.6447467295  2.4395728111  1200          0.2950364010 
0.5578465060  0.8629758615  0.9917610711  0.8247422680  0.5704467354  0.5452462772  0.9853603604  0.8996617813  0.9810671256  0.8645235362  24.716786817  1.5073454281  2.4395728111  1500          0.2853483335 
0.5569873995  0.8711296003  0.9943357364  0.8185567010  0.5710194731  0.5429553265  0.9864864865  0.9188275085  0.9827882960  0.8760045924  29.660144181  1.4160069676  2.4395728111  1800          0.2886409561 
0.5589919814  0.8715448438  0.9953656025  0.8391752577  0.5727376861  0.5452462772  0.9873310811  0.9109357384  0.9896729776  0.8645235362  34.603501544  1.3479881457  2.4395728111  2100          0.2821937823 
0.5598510879  0.8690369618  0.9938208033  0.8247422680  0.5733104238  0.5463917526  0.9898648649  0.9098083427  0.9905335628  0.8725602755  39.546858908  1.2945879606  2.4395728111  2400          0.2861206476 
0.5638602517  0.8693346419  0.9933058702  0.8268041237  0.5767468499  0.5509736541  0.9923986486  0.9109357384  0.9913941480  0.8702640643  44.490216271  1.2586945085  2.4395728111  2700          0.3008388917 
0.5664375713  0.8708952448  0.9933058702  0.8247422680  0.5796105384  0.5532646048  0.9915540541  0.9188275085  0.9896729776  0.8691159587  49.433573635  1.2223628656  2.4395728111  3000          0.2886649601 
0.5670103090  0.8736145903  0.9953656025  0.8350515464  0.5796105384  0.5544100802  0.9926801802  0.9109357384  0.9936890419  0.8748564868  54.376930999  1.1858542005  2.4395728111  3300          0.2864385915 
0.5674398623  0.8789002138  0.9938208033  0.8474226804  0.5793241695  0.5555555556  0.9946509009  0.9086809470  0.9939759036  0.8805970149  59.320288362  1.1642939395  2.4395728111  3600          0.2994386864 
0.5703035507  0.8710137957  0.9953656025  0.8329896907  0.5804696449  0.5601374570  0.9943693694  0.9109357384  0.9959839357  0.8691159587  64.263645726  1.1039210755  5.3998112679  3900          0.2939368343 
0.5688717065  0.8739558723  0.9953656025  0.8350515464  0.5810423826  0.5567010309  0.9946509009  0.9177001127  0.9948364888  0.8691159587  69.207003089  0.9405522029  5.3998112679  4200          0.2958103808 
0.5691580753  0.8768888635  0.9958805355  0.8391752577  0.5827605956  0.5555555556  0.9943693694  0.9131905299  0.9951233505  0.8783008037  74.150360453  0.8760276784  5.3998112679  4500          0.2995470103 
0.5684421532  0.8780864870  0.9958805355  0.8474226804  0.5824742268  0.5544100802  0.9960585586  0.9165727170  0.9956970740  0.8702640643  79.093717816  0.8353170705  5.3998112679  4800          0.3006766438 
0.5678694155  0.8736076869  0.9958805355  0.8350515464  0.5836197022  0.5521191294  0.9969031532  0.9120631342  0.9962707975  0.8737083812  82.389289392  0.8062681061  5.3998112679  5000          0.3045746922 
