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: 1
	output_dir: sweep/ablation3/outputs/a811730f8f058cf4a77c84d81221e46c
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 978951233
	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: 0.6880433961757358
	lambda2: 0.9840350138898164
	last_k_epoch: 0.33648211095401626
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3.599417945900826
	weight_decay: 0.0001
	worst_case_p: 0.25
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    
0.0108820160  0.0156771776  0.0216271885  0.0185567010  0.0103092784  0.0114547537  0.0163288288  0.0124013529  0.0152036718  0.0160734788  0.0000000000  9.4458351135  2.0088801384  0             1.6339721680 
0.5032932414  0.8127538828  0.8964984552  0.7546391753  0.5174684994  0.4891179840  0.9096283784  0.8478015784  0.8763625932  0.8358208955  4.9433573635  5.7242688473  2.2550172806  300           0.3109008964 
0.5506872849  0.8507291943  0.9757981462  0.8061855670  0.5675830470  0.5337915235  0.9597409910  0.8895152198  0.9546758462  0.8564867968  9.8867147271  2.9045254397  2.2550172806  600           0.3016485739 
0.5544100799  0.8743097662  0.9907312049  0.8268041237  0.5715922108  0.5372279496  0.9735360360  0.9109357384  0.9718875502  0.8851894374  14.830072090  2.2013425235  2.2550172806  900           0.2996871360 
0.5608533789  0.8765911834  0.9943357364  0.8371134021  0.5776059565  0.5441008018  0.9836711712  0.9120631342  0.9799196787  0.8805970149  19.773429454  1.9289695112  2.2550172806  1200          0.3033293160 
0.5627147764  0.8776749771  0.9958805355  0.8391752577  0.5767468499  0.5486827033  0.9870495495  0.9098083427  0.9873780838  0.8840413318  24.716786817  1.7591557455  2.2550172806  1500          0.3034947522 
0.5694444442  0.8751453978  0.9963954686  0.8350515464  0.5787514318  0.5601374570  0.9893018018  0.9109357384  0.9873780838  0.8794489093  29.660144181  1.6647225805  2.2550172806  1800          0.3089187654 
0.5715922105  0.8763440087  0.9948506694  0.8329896907  0.5796105384  0.5635738832  0.9923986486  0.9154453213  0.9916810098  0.8805970149  34.603501544  1.5924451486  2.2550172806  2100          0.2956364059 
0.5738831612  0.8803629757  0.9943357364  0.8371134021  0.5841924399  0.5635738832  0.9938063063  0.9210822999  0.9925415950  0.8828932262  39.546858908  1.5503287621  2.2550172806  2400          0.2940608891 
0.5757445587  0.8842395124  0.9953656025  0.8453608247  0.5856242841  0.5658648339  0.9935247748  0.9244644870  0.9934021801  0.8828932262  44.490216271  1.4784354202  2.2550172806  2700          0.2988664126 
0.5764604808  0.8767129040  0.9953656025  0.8329896907  0.5859106529  0.5670103093  0.9954954955  0.9177001127  0.9945496271  0.8794489093  49.433573635  1.4338743444  2.2550172806  3000          0.3025505797 
0.5771764029  0.8787806755  0.9958805355  0.8494845361  0.5861970218  0.5681557847  0.9971846847  0.9154453213  0.9959839357  0.8714121699  54.376930999  1.3712292413  2.2550172806  3300          0.2972582968 
0.5767468497  0.8774278024  0.9974253347  0.8350515464  0.5864833906  0.5670103093  0.9957770270  0.9131905299  0.9962707975  0.8840413318  59.320288362  1.2536566989  5.3966603279  3600          0.3119753067 
0.5790378004  0.8865347362  0.9969104016  0.8556701031  0.5887743414  0.5693012600  0.9954954955  0.9233370913  0.9954102123  0.8805970149  64.263645726  1.1324453811  5.3966603279  3900          0.3072414978 
0.5814719356  0.8857555258  0.9963954686  0.8556701031  0.5924971363  0.5704467354  0.9952139640  0.9255918828  0.9974182444  0.8760045924  69.207003089  1.0616585054  5.3966603279  4200          0.3025548617 
0.5821878577  0.8809078305  0.9963954686  0.8432989691  0.5927835052  0.5715922108  0.9971846847  0.9188275085  0.9959839357  0.8805970149  74.150360453  1.0081528950  5.3966603279  4500          0.2984786948 
0.5827605954  0.8835926595  0.9953656025  0.8536082474  0.5927835052  0.5727376861  0.9974662162  0.9165727170  0.9977051061  0.8805970149  79.093717816  0.9581744655  5.3966603279  4800          0.3020076553 
0.5829037798  0.8853292219  0.9958805355  0.8577319588  0.5919243986  0.5738831615  0.9977477477  0.9199549042  0.9956970740  0.8783008037  82.389289392  0.9254774818  5.3966603279  5000          0.3000416052 
