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: 0
	output_dir: sweep/ablation3/outputs/427f452e1918510778af602bd34a99bc
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1289538529
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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: 0.5
	lambda2: 0.5
	last_k_epoch: 0.25
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3
	weight_decay: 0.0
	worst_case_p: 0.3333333333333333
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    
0.0130297824  0.0188664289  0.0221421215  0.0247422680  0.0168957617  0.0091638030  0.0106981982  0.0157835400  0.0154905336  0.0160734788  0.0000000000  7.1063547134  2.3353104591  0             1.5921339989 
0.5329324167  0.8288453163  0.9181256437  0.8041237113  0.5332187858  0.5326460481  0.9214527027  0.8511837655  0.9044750430  0.8312284730  4.9433573635  4.2096984537  2.5970582962  300           0.2966937272 
0.5579896904  0.8707565480  0.9824922760  0.8412371134  0.5604238259  0.5555555556  0.9653716216  0.9019165727  0.9552495697  0.8691159587  9.8867147271  1.8572352537  2.5970582962  600           0.3073887928 
0.5608533789  0.8833375940  0.9891864058  0.8597938144  0.5672966781  0.5544100802  0.9802927928  0.9199549042  0.9730349971  0.8702640643  14.830072090  1.4314946890  2.5970582962  900           0.2912993908 
0.5615693010  0.8898871279  0.9933058702  0.8577319588  0.5744558992  0.5486827033  0.9856418919  0.9255918828  0.9873780838  0.8863375431  19.773429454  1.2604480513  2.5970582962  1200          0.3025288709 
0.5645761738  0.8895182326  0.9938208033  0.8577319588  0.5770332188  0.5521191294  0.9898648649  0.9233370913  0.9888123924  0.8874856487  24.716786817  1.1619483564  2.5970582962  1500          0.2931218354 
0.5665807557  0.8859186662  0.9943357364  0.8515463918  0.5787514318  0.5544100802  0.9926801802  0.9244644870  0.9919678715  0.8817451206  29.660144181  1.0980343374  2.5970582962  1800          0.3086814308 
0.5691580753  0.8981148281  0.9953656025  0.8721649485  0.5816151203  0.5567010309  0.9923986486  0.9301014656  0.9939759036  0.8920780712  34.603501544  1.0669486056  2.5970582962  2100          0.3042123564 
0.5721649482  0.8948713378  0.9948506694  0.8556701031  0.5841924399  0.5601374570  0.9943693694  0.9368658399  0.9951233505  0.8920780712  39.546858908  1.0285640611  2.5970582962  2400          0.2844976624 
0.5728808703  0.8931347754  0.9953656025  0.8515463918  0.5833333333  0.5624284078  0.9943693694  0.9334836528  0.9945496271  0.8943742824  44.490216271  0.9884121889  2.5970582962  2700          0.3012924282 
0.5741695301  0.9020083410  0.9969104016  0.8680412371  0.5859106529  0.5624284078  0.9954954955  0.9447576099  0.9951233505  0.8932261768  49.433573635  0.9610871567  2.5970582962  3000          0.3069130254 
0.5754581899  0.8953656872  0.9963954686  0.8639175258  0.5884879725  0.5624284078  0.9960585586  0.9301014656  0.9962707975  0.8920780712  54.376930999  0.9383036562  2.5970582962  3300          0.3036799010 
0.5766036652  0.8956505481  0.9953656025  0.8556701031  0.5896334479  0.5635738832  0.9963400901  0.9346110485  0.9951233505  0.8966704937  59.320288362  0.9256221487  2.5970582962  3600          0.2986887097 
0.5774627718  0.9007661280  0.9974253347  0.8721649485  0.5890607102  0.5658648339  0.9952139640  0.9346110485  0.9962707975  0.8955223881  64.263645726  0.8614523153  5.3944554329  3900          0.2942150529 
0.5780355094  0.9015246285  0.9963954686  0.8721649485  0.5902061856  0.5658648339  0.9963400901  0.9357384442  0.9942627653  0.8966704937  69.207003089  0.7236717735  5.3944554329  4200          0.3015034787 
0.5786082471  0.8996823343  0.9958805355  0.8701030928  0.5902061856  0.5670103093  0.9946509009  0.9368658399  0.9959839357  0.8920780712  74.150360453  0.6804699840  5.3944554329  4500          0.3045911654 
0.5796105381  0.9005120500  0.9953656025  0.8680412371  0.5910652921  0.5681557847  0.9963400901  0.9391206313  0.9956970740  0.8943742824  79.093717816  0.6496726197  5.3944554329  4800          0.3116750272 
0.5816151200  0.8968629657  0.9958805355  0.8536082474  0.5916380298  0.5715922108  0.9977477477  0.9368658399  0.9962707975  0.9001148106  82.389289392  0.6306998512  5.3944554329  5000          0.2998177445 
