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: 1
	output_dir: sweep/ablation3/outputs/b6458bb02dea4547190c10af5d2c7a94
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1306662544
	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: 0.6880433961757358
	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 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    
0.0133935681  0.0276695401  0.0164778579  0.0103092784  0.0223367698  0.0160366552  0.0382882883  0.0417136415  0.0298336202  0.0252583238  0.0000000000  9.3964796066  2.0088801384  0             1.4575402737 
0.6270016029  0.7690784703  0.6168898043  0.6371134021  0.7981099656  0.6781214204  0.8704954955  0.8151071026  0.8700516351  0.8140068886  4.9433573635  5.7462010980  2.2550172806  300           0.2855346576 
0.6870199706  0.8340042664  0.6812564367  0.6927835052  0.9117983963  0.7663230241  0.9527027027  0.8883878241  0.9434882387  0.8473019518  9.8867147271  3.2078231724  2.2550172806  600           0.2925866747 
0.6970632886  0.8541810645  0.6972193615  0.6969072165  0.9412943872  0.7880870561  0.9701576577  0.9030439684  0.9652897303  0.8714121699  14.830072090  2.4252938569  2.2550172806  900           0.2891070302 
0.7145826915  0.8560686035  0.7095777549  0.7195876289  0.9533218786  0.7949599084  0.9797297297  0.9064261556  0.9804934022  0.8668197474  19.773429454  2.0580236049  2.2550172806  1200          0.2984176167 
0.7202512020  0.8697326772  0.7126673532  0.7278350515  0.9667812142  0.8075601375  0.9884572072  0.9233370913  0.9819277108  0.8783008037  24.716786817  1.8442205246  2.2550172806  1500          0.2902005514 
0.7212810682  0.8637043399  0.7147270855  0.7278350515  0.9710767468  0.8098510882  0.9864864865  0.9075535513  0.9888123924  0.8737083812  29.660144181  1.7087367586  2.2550172806  1800          0.2951011260 
0.7256611843  0.8644197778  0.7173017508  0.7340206186  0.9756586483  0.8029782360  0.9907094595  0.9165727170  0.9899598394  0.8737083812  34.603501544  1.6098227179  2.2550172806  2100          0.2938735112 
0.7282390347  0.8624985990  0.7162718847  0.7402061856  0.9773768614  0.7949599084  0.9912725225  0.9188275085  0.9902467011  0.8737083812  39.546858908  1.5640736679  2.2550172806  2400          0.2925356674 
0.7297848956  0.8701378425  0.7173017508  0.7422680412  0.9782359679  0.8052691867  0.9946509009  0.9199549042  0.9934021801  0.8851894374  44.490216271  1.4937548463  2.2550172806  2700          0.2975746751 
0.7292689009  0.8670875145  0.7183316169  0.7402061856  0.9825315006  0.7995418099  0.9943693694  0.9188275085  0.9956970740  0.8828932262  49.433573635  1.4537160357  2.2550172806  3000          0.3067369270 
0.7313296948  0.8724486264  0.7203913491  0.7422680412  0.9831042383  0.8132875143  0.9954954955  0.9165727170  0.9956970740  0.8874856487  54.376930999  1.4039575108  2.2550172806  3300          0.2948141448 
0.7349363497  0.8681942003  0.7234809475  0.7463917526  0.9836769759  0.7995418099  0.9954954955  0.9255918828  0.9945496271  0.8794489093  59.320288362  1.2774908996  5.3966603279  3600          0.2949585072 
0.7328744940  0.8693655354  0.7234809475  0.7422680412  0.9839633448  0.8052691867  0.9954954955  0.9210822999  0.9956970740  0.8817451206  64.263645726  1.1404766130  5.3966603279  3900          0.3096893493 
0.7315871613  0.8682181958  0.7209062822  0.7422680412  0.9831042383  0.8132875143  0.9954954955  0.9199549042  0.9942627653  0.8714121699  69.207003089  1.0659967897  5.3966603279  4200          0.2998087811 
0.7323606226  0.8674658327  0.7203913491  0.7443298969  0.9836769759  0.8052691867  0.9952139640  0.9188275085  0.9956970740  0.8783008037  74.150360453  1.0165663020  5.3966603279  4500          0.2999417543 
0.7318467513  0.8735949785  0.7173017508  0.7463917526  0.9865406644  0.8155784651  0.9969031532  0.9165727170  0.9962707975  0.8886337543  79.093717816  0.9780308078  5.3966603279  4800          0.2969451125 
0.7326191509  0.8708971090  0.7188465499  0.7463917526  0.9845360825  0.8132875143  0.9957770270  0.9199549042  0.9971313827  0.8794489093  82.389289392  0.9393944135  5.3966603279  5000          0.2991396892 
