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: [3]
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: 4
	output_dir: sweep/ablation3/outputs/b464f805bf6122c92ac85e019b45551f
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1979513661
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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: 0.8001163740830898
	lambda2: 0.7340462818445315
	last_k_epoch: 0.3149495809125332
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.8284464949429635
	weight_decay: 1e-06
	worst_case_p: 0.2
using augment transform
using augment transform
using augment transform
using normal 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    
0.2286788301  0.1534912850  0.1043319097  0.1295843521  0.1673773987  0.1901709402  0.1384730539  0.1407185629  0.2242366412  0.2331210191  0.0000000000  10.995084762  1.7945718765  0             1.5661125183 
0.7789701541  0.9609615739  0.9676632093  0.9388753056  0.9706823028  0.9529914530  0.9977544910  0.9910179641  0.7668575064  0.7910828025  7.1856287425  3.5545877850  2.0946040154  300           0.1497129162 
0.7827885687  0.9659698113  0.9896278218  0.9462102689  0.9888059701  0.9636752137  1.0000000000  0.9880239521  0.7719465649  0.7936305732  14.371257485  1.1236554386  2.0946040154  600           0.1641300042 
0.7864503813  0.9699040467  0.9932885906  0.9584352078  0.9914712154  0.9572649573  0.9992514970  0.9940119760  0.7729007634  0.8000000000  21.556886227  0.9659333225  2.0946040154  900           0.1642883952 
0.7909065489  0.9721435441  0.9963392312  0.9608801956  0.9941364606  0.9615384615  0.9992514970  0.9940119760  0.7767175573  0.8050955414  28.742514970  0.8658816112  2.0946040154  1200          0.1646958542 
0.7948839966  0.9723490345  0.9945088469  0.9657701711  0.9914712154  0.9572649573  1.0000000000  0.9940119760  0.7821246819  0.8076433121  35.928143712  0.8627828036  2.0946040154  1500          0.1625241828 
0.7999762966  0.9766450211  0.9969493594  0.9731051345  0.9920042644  0.9658119658  1.0000000000  0.9910179641  0.7872137405  0.8127388535  43.113772455  0.7885368925  2.0946040154  1800          0.1638591266 
0.8025232569  0.9742802962  0.9981696156  0.9608801956  0.9962686567  0.9679487179  1.0000000000  0.9940119760  0.7884860051  0.8165605096  50.299401197  0.7760269732  2.0946040154  2100          0.1640339764 
0.8072974907  0.9820192746  0.9969493594  0.9755501222  0.9968017058  0.9764957265  1.0000000000  0.9940119760  0.7929389313  0.8216560510  57.485029940  0.7772057159  2.0946040154  2400          0.1638303916 
0.8136636760  0.9729740566  0.9969493594  0.9535452323  0.9973347548  0.9743589744  1.0000000000  0.9910179641  0.7980279898  0.8292993631  64.670658682  0.7389184376  2.0946040154  2700          0.1642889905 
0.8192330752  0.9742802962  0.9993898719  0.9608801956  0.9968017058  0.9679487179  1.0000000000  0.9940119760  0.8040712468  0.8343949045  71.856287425  0.7163693756  2.0946040154  3000          0.1651991796 
0.8205069606  0.9753007826  0.9969493594  0.9682151589  0.9978678038  0.9636752137  1.0000000000  0.9940119760  0.8040712468  0.8369426752  79.041916167  0.7214461606  2.0946040154  3300          0.1649431841 
0.8216201921  0.9745660495  0.9993898719  0.9608801956  0.9968017058  0.9658119658  1.0000000000  0.9970059880  0.8062977099  0.8369426752  86.227544910  0.5955411004  5.4003272057  3600          0.1916028261 
0.8227342340  0.9776205428  0.9951189750  0.9657701711  0.9984008529  0.9700854701  1.0000000000  0.9970059880  0.8072519084  0.8382165605  93.413173652  0.4298946410  5.4003272057  3900          0.2107773407 
0.8230523002  0.9721435441  0.9981696156  0.9608801956  0.9989339019  0.9615384615  0.9992514970  0.9940119760  0.8078880407  0.8382165605  100.59880239  0.3926604861  5.4003272057  4200          0.2088747080 
0.8243245648  0.9731795470  0.9987797437  0.9584352078  0.9984008529  0.9700854701  0.9992514970  0.9910179641  0.8104325700  0.8382165605  107.78443113  0.3647413927  5.4003272057  4500          0.2083502245 
0.8251205406  0.9748095389  0.9981696156  0.9633251834  0.9984008529  0.9700854701  1.0000000000  0.9910179641  0.8107506361  0.8394904459  114.97005988  0.3455867396  5.4003272057  4800          0.2087328490 
0.8271895913  0.9722462893  0.9981696156  0.9633251834  0.9989339019  0.9594017094  1.0000000000  0.9940119760  0.8123409669  0.8420382166  119.76047904  0.3338813143  5.4003272057  5000          0.2087183821 
