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: 3
	output_dir: sweep/ablation3/outputs/944b3441e56a47d03f3bef8b4ec27186
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 180200480
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	trial_seed: 2
	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: 0.5694511041907044
	lambda2: 0.6621108818243455
	last_k_epoch: 0.20248994529588413
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.502579147595572
	weight_decay: 0.0001
	worst_case_p: 0.2
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    
0.1355782269  0.1141874941  0.1293471629  0.1418092910  0.1146055437  0.1132478632  0.1347305389  0.1197604790  0.1001908397  0.1095541401  0.0000000000  8.7277936935  1.7945718765  0             1.4968924522 
0.9102328477  0.9631046685  0.9060402685  0.9144254279  0.9813432836  0.9658119658  0.9985029940  0.9910179641  0.9659669211  0.9324840764  7.1856287425  3.1106885837  2.0936598778  300           0.1411978714 
0.9316074708  0.9719083415  0.9267846248  0.9364303178  0.9952025586  0.9722222222  1.0000000000  0.9970059880  0.9777353690  0.9464968153  14.371257485  1.1023124013  2.0936598778  600           0.1614732909 
0.9364952088  0.9794399982  0.9292251373  0.9437652812  0.9952025586  0.9829059829  1.0000000000  1.0000000000  0.9821882952  0.9554140127  21.556886227  0.8932070114  2.0936598778  900           0.1633048447 
0.9395480870  0.9761818458  0.9328859060  0.9462102689  0.9973347548  0.9850427350  1.0000000000  0.9970059880  0.9869592875  0.9464968153  28.742514970  0.8774575596  2.0936598778  1200          0.1632628902 
0.9416857731  0.9693469609  0.9347162904  0.9486552567  0.9984008529  0.9658119658  1.0000000000  0.9970059880  0.9901399491  0.9452229299  35.928143712  0.7846849105  2.0936598778  1500          0.1636909620 
0.9429082670  0.9753307199  0.9347162904  0.9511002445  0.9973347548  0.9807692308  1.0000000000  1.0000000000  0.9888676845  0.9452229299  43.113772455  0.8031167612  2.0936598778  1800          0.1633468469 
0.9395458494  0.9761799768  0.9353264185  0.9437652812  0.9984008529  0.9807692308  1.0000000000  1.0000000000  0.9907760814  0.9477707006  50.299401197  0.7663740146  2.0936598778  2100          0.1650754611 
0.9392407853  0.9727594674  0.9347162904  0.9437652812  1.0000000000  0.9764957265  1.0000000000  0.9940119760  0.9936386768  0.9477707006  57.485029940  0.7101634779  2.0936598778  2400          0.1647346632 
0.9380182914  0.9756066013  0.9347162904  0.9413202934  0.9994669510  0.9807692308  1.0000000000  0.9970059880  0.9939567430  0.9490445860  64.670658682  0.6789787212  2.0936598778  2700          0.1634349640 
0.9358783677  0.9748943506  0.9353264185  0.9364303178  1.0000000000  0.9786324786  1.0000000000  0.9970059880  0.9952290076  0.9490445860  71.856287425  0.6972287940  2.0936598778  3000          0.1629900710 
0.9367957976  0.9739062185  0.9347162904  0.9388753056  1.0000000000  0.9764957265  1.0000000000  1.0000000000  0.9968193384  0.9452229299  79.041916167  0.7614325624  2.0936598778  3300          0.1636092043 
0.9392407853  0.9773032461  0.9347162904  0.9437652812  0.9984008529  0.9764957265  1.0000000000  1.0000000000  0.9955470738  0.9554140127  86.227544910  0.7003524883  2.0936598778  3600          0.1619035300 
0.9355755413  0.9788783636  0.9322757779  0.9388753056  0.9989339019  0.9850427350  1.0000000000  1.0000000000  0.9968193384  0.9515923567  93.413173652  0.6255323170  2.0936598778  3900          0.1602329652 
0.9377132274  0.9768922275  0.9341061623  0.9413202934  0.9994669510  0.9829059829  1.0000000000  1.0000000000  0.9971374046  0.9477707006  100.59880239  0.4858099990  5.3983359337  4200          0.1920473997 
0.9377132274  0.9791542449  0.9341061623  0.9413202934  1.0000000000  0.9850427350  1.0000000000  0.9970059880  0.9968193384  0.9554140127  107.78443113  0.3595525545  5.3983359337  4500          0.2048324275 
0.9367980352  0.9807274935  0.9322757779  0.9413202934  0.9994669510  0.9893162393  1.0000000000  1.0000000000  0.9974554707  0.9528662420  114.97005988  0.3270388169  5.3983359337  4800          0.2055330300 
0.9349654132  0.9740432247  0.9310555217  0.9388753056  0.9994669510  0.9743589744  1.0000000000  1.0000000000  0.9971374046  0.9477707006  119.76047904  0.3053308111  5.3983359337  5000          0.2049060822 
