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: PACS
	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/8aee5829a49546721c2d035cc007bfb7
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 2017552276
	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    
0.1578725175  0.1247206387  0.1470408786  0.1687041565  0.1348614072  0.1410256410  0.1796407186  0.1197604790  0.1151399491  0.1133757962  0.0000000000  7.5834264755  2.3338298798  0             1.9977829456 
0.9138980917  0.9684878321  0.9084807810  0.9193154034  0.9840085288  0.9679487179  0.9985029940  0.9910179641  0.9573791349  0.9464968153  7.1856287425  1.8692873732  2.5978608131  300           0.1598984035 
0.9291647207  0.9765675136  0.9243441123  0.9339853301  0.9920042644  0.9700854701  1.0000000000  0.9940119760  0.9761450382  0.9656050955  14.371257485  0.7507179495  2.5978608131  600           0.1799696978 
0.9337451569  0.9799664101  0.9286150092  0.9388753056  0.9946695096  0.9743589744  1.0000000000  0.9910179641  0.9853689567  0.9745222930  21.556886227  0.6314643912  2.5978608131  900           0.1794289319 
0.9346625867  0.9785555186  0.9280048810  0.9413202934  0.9973347548  0.9764957265  1.0000000000  0.9910179641  0.9837786260  0.9681528662  28.742514970  0.5966115116  2.5978608131  1200          0.1787000600 
0.9303805017  0.9761447541  0.9316656498  0.9290953545  0.9968017058  0.9743589744  1.0000000000  0.9910179641  0.9895038168  0.9630573248  35.928143712  0.5670809637  2.5978608131  1500          0.1772947486 
0.9303827393  0.9819624181  0.9292251373  0.9315403423  0.9994669510  0.9743589744  1.0000000000  0.9970059880  0.9907760814  0.9745222930  43.113772455  0.5370063941  2.5978608131  1800          0.1782752514 
0.9267174953  0.9784030336  0.9267846248  0.9266503667  0.9989339019  0.9679487179  1.0000000000  0.9940119760  0.9904580153  0.9732484076  50.299401197  0.5141841800  2.5978608131  2100          0.1793267608 
0.9282428156  0.9816766649  0.9298352654  0.9266503667  0.9978678038  0.9764957265  1.0000000000  0.9940119760  0.9942748092  0.9745222930  57.485029940  0.5056634358  2.5978608131  2400          0.1778765583 
0.9276326875  0.9812520364  0.9286150092  0.9266503667  0.9984008529  0.9764957265  1.0000000000  0.9940119760  0.9930025445  0.9732484076  64.670658682  0.4926443927  2.5978608131  2700          0.1790850465 
0.9288551814  0.9825259218  0.9286150092  0.9290953545  0.9994669510  0.9764957265  1.0000000000  0.9940119760  0.9942748092  0.9770700637  71.856287425  0.4878700100  2.5978608131  3000          0.1785216665 
0.9300732000  0.9806786609  0.9334960342  0.9266503667  0.9989339019  0.9764957265  1.0000000000  0.9910179641  0.9952290076  0.9745222930  79.041916167  0.4852596639  2.5978608131  3300          0.1771197581 
0.9291557702  0.9819642871  0.9341061623  0.9242053790  0.9994669510  0.9786324786  1.0000000000  0.9940119760  0.9965012723  0.9732484076  86.227544910  0.5728072843  2.5978608131  3600          0.1757635530 
0.9273231482  0.9802540324  0.9328859060  0.9217603912  1.0000000000  0.9764957265  1.0000000000  0.9910179641  0.9968193384  0.9732484076  93.413173652  0.3842847037  5.3944354057  3900          0.1916236313 
0.9282405780  0.9829505502  0.9322757779  0.9242053790  0.9994669510  0.9764957265  1.0000000000  0.9940119760  0.9965012723  0.9783439490  100.59880239  0.2751550910  5.3944354057  4200          0.2071360644 
0.9300732000  0.9801151572  0.9334960342  0.9266503667  0.9989339019  0.9743589744  1.0000000000  0.9940119760  0.9974554707  0.9719745223  107.78443113  0.2535408656  5.3944354057  4500          0.2067072161 
0.9303805017  0.9809780240  0.9316656498  0.9290953545  1.0000000000  0.9807692308  1.0000000000  0.9940119760  0.9968193384  0.9681528662  114.97005988  0.2403893441  5.3944354057  4800          0.2077596323 
0.9294630719  0.9831011663  0.9322757779  0.9266503667  1.0000000000  0.9807692308  1.0000000000  0.9940119760  0.9968193384  0.9745222930  119.76047904  0.2362883960  5.3944354057  5000          0.2158076191 
