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: 0
	output_dir: sweep/ablation3/outputs/586789c2723541cc004aedb82774085a
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1267994738
	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: 0.5
	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 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    
0.0095294467  0.0117945037  0.0128733265  0.0061855670  0.0146048110  0.0183276060  0.0090090090  0.0090191657  0.0094664372  0.0080367394  0.0000000000  8.4835405350  2.3353104591  0             1.5936882496 
0.6697654662  0.7929045548  0.6549948507  0.6845360825  0.8316151203  0.6975945017  0.9189189189  0.8590755355  0.8978772232  0.8220436280  4.9433573635  4.3721371547  2.5970582962  300           0.2847729365 
0.7094386695  0.8423822878  0.6889804325  0.7298969072  0.9246849943  0.7663230241  0.9642454955  0.8951521984  0.9595524957  0.8656716418  9.8867147271  2.1161632617  2.5970582962  600           0.3026950471 
0.7269591341  0.8553240204  0.6992790937  0.7546391753  0.9493127148  0.7857961054  0.9783220721  0.9041713641  0.9779116466  0.8760045924  14.830072090  1.5812537920  2.5970582962  900           0.2860719705 
0.7339139156  0.8568134080  0.7070030896  0.7608247423  0.9619129439  0.7857961054  0.9856418919  0.9109357384  0.9827882960  0.8737083812  19.773429454  1.3515219287  2.5970582962  1200          0.3033095423 
0.7362300526  0.8636845068  0.7136972194  0.7587628866  0.9699312715  0.8087056128  0.9893018018  0.9109357384  0.9870912220  0.8714121699  24.716786817  1.2327664940  2.5970582962  1500          0.2995605930 
0.7403537639  0.8720245047  0.7136972194  0.7670103093  0.9727949599  0.8132875143  0.9912725225  0.9233370913  0.9908204246  0.8794489093  29.660144181  1.1650833688  2.5970582962  1800          0.3000940688 
0.7424156196  0.8693716727  0.7136972194  0.7711340206  0.9759450172  0.7972508591  0.9935247748  0.9210822999  0.9902467011  0.8897818599  34.603501544  1.0977421711  2.5970582962  2100          0.3001448917 
0.7437018905  0.8746835847  0.7183316169  0.7690721649  0.9799541810  0.8121420389  0.9940878378  0.9267192785  0.9945496271  0.8851894374  39.546858908  1.0716037041  2.5970582962  2400          0.2880016557 
0.7462776176  0.8701645789  0.7214212152  0.7711340206  0.9819587629  0.8064146621  0.9949324324  0.9154453213  0.9939759036  0.8886337543  44.490216271  1.0243255214  2.5970582962  2700          0.2909421102 
0.7447306949  0.8689699037  0.7224510814  0.7670103093  0.9819587629  0.8041237113  0.9963400901  0.9233370913  0.9954102123  0.8794489093  49.433573635  0.9945104500  2.5970582962  3000          0.2902542075 
0.7447306949  0.8731510237  0.7224510814  0.7670103093  0.9831042383  0.8144329897  0.9963400901  0.9267192785  0.9954102123  0.8783008037  54.376930999  0.9782271892  2.5970582962  3300          0.2902193197 
0.7449870998  0.8643947948  0.7250257467  0.7649484536  0.9845360825  0.7995418099  0.9963400901  0.9210822999  0.9956970740  0.8725602755  59.320288362  0.9511136703  2.5970582962  3600          0.2894054699 
0.7462744324  0.8776933695  0.7276004119  0.7649484536  0.9839633448  0.8167239404  0.9960585586  0.9346110485  0.9968445209  0.8817451206  64.263645726  0.8714777182  5.3944554329  3900          0.2942907556 
0.7470478937  0.8746636408  0.7270854789  0.7670103093  0.9836769759  0.8201603666  0.9963400901  0.9289740699  0.9956970740  0.8748564868  69.207003089  0.7452652474  5.3944554329  4200          0.2917567404 
0.7478213550  0.8770005058  0.7265705458  0.7690721649  0.9871134021  0.8121420389  0.9957770270  0.9233370913  0.9965576592  0.8955223881  74.150360453  0.6972541982  5.3944554329  4500          0.2922349691 
0.7470478937  0.8708565659  0.7270854789  0.7670103093  0.9862542955  0.8121420389  0.9974662162  0.9267192785  0.9968445209  0.8737083812  79.093717816  0.6675700734  5.3944554329  4800          0.2994643998 
0.7467904272  0.8765790144  0.7265705458  0.7670103093  0.9859679267  0.8087056128  0.9971846847  0.9301014656  0.9971313827  0.8909299656  82.389289392  0.6519300416  5.3944554329  5000          0.2910600495 
