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: [2]
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: 2
	output_dir: sweep/ablation3/outputs/b9743b4141b39064496fcc7cb48f1dc2
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 536917322
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	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: 0.7419102898692578
	lambda2: 0.5215383105176172
	last_k_epoch: 0.23762453204831346
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.9748462276330736
	weight_decay: 1e-06
	worst_case_p: 0.3
using augment transform
using augment transform
using normal 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    
0.1822604790  0.1493902881  0.1873093350  0.1735941320  0.1871002132  0.1752136752  0.1758982036  0.1886227545  0.0833333333  0.0993630573  0.0000000000  8.9273748398  2.1691875458  0             1.6349110603 
0.9921407181  0.9486003643  0.9816961562  0.9633251834  0.9722814499  0.9487179487  0.9932634731  0.9910179641  0.9561068702  0.9337579618  7.1856287425  2.8742796260  2.4380745888  300           0.1609049654 
0.9902694606  0.9544218040  0.9902379500  0.9535452323  0.9882729211  0.9594017094  0.9925149701  0.9880239521  0.9627862595  0.9503184713  14.371257485  1.1047181328  2.4380745888  600           0.1812704309 
0.9925149696  0.9658454323  0.9938987187  0.9682151589  0.9941364606  0.9700854701  0.9940119760  0.9910179641  0.9697837150  0.9592356688  21.556886227  0.9395989597  2.4380745888  900           0.1802799988 
0.9940119756  0.9619759431  0.9963392312  0.9608801956  0.9920042644  0.9658119658  0.9940119760  0.9940119760  0.9716921120  0.9592356688  28.742514970  0.8754546748  2.4380745888  1200          0.1795290430 
0.9921407181  0.9562709339  0.9932885906  0.9535452323  0.9925373134  0.9636752137  0.9932634731  0.9910179641  0.9786895674  0.9515923567  35.928143712  0.8361355323  2.4380745888  1500          0.1776149686 
0.9917664666  0.9624347948  0.9969493594  0.9682151589  0.9968017058  0.9636752137  0.9925149701  0.9910179641  0.9790076336  0.9554140127  43.113772455  0.8024478406  2.4380745888  1800          0.1762949522 
0.9917664666  0.9686808252  0.9957291031  0.9682151589  0.9957356077  0.9722222222  0.9925149701  0.9910179641  0.9825063613  0.9656050955  50.299401197  0.7723726592  2.4380745888  2100          0.1755826704 
0.9917664666  0.9673590690  0.9987797437  0.9706601467  0.9973347548  0.9658119658  0.9925149701  0.9910179641  0.9828244275  0.9656050955  57.485029940  0.7421205012  2.4380745888  2400          0.1748162564 
0.9925149696  0.9672357104  1.0000000000  0.9608801956  0.9968017058  0.9764957265  0.9940119760  0.9910179641  0.9805979644  0.9643312102  64.670658682  0.7211710160  2.4380745888  2700          0.1732112304 
0.9925149696  0.9699547106  0.9993898719  0.9682151589  0.9989339019  0.9722222222  0.9940119760  0.9910179641  0.9828244275  0.9694267516  71.856287425  0.7210316547  2.4380745888  3000          0.1752350974 
0.9925149696  0.9664891988  0.9987797437  0.9633251834  0.9968017058  0.9743589744  0.9940119760  0.9910179641  0.9844147583  0.9617834395  79.041916167  0.7199990645  2.4380745888  3300          0.1715932496 
0.9940119756  0.9614827927  0.9975594875  0.9657701711  0.9978678038  0.9658119658  0.9940119760  0.9940119760  0.9856870229  0.9528662420  86.227544910  0.7079334086  2.4380745888  3600          0.1713665136 
0.9936377241  0.9641811795  0.9993898719  0.9657701711  0.9984008529  0.9700854701  0.9932634731  0.9940119760  0.9847328244  0.9566878981  93.413173652  0.6261819901  5.3979983330  3900          0.1809056425 
0.9936377241  0.9697834434  0.9993898719  0.9706601467  0.9989339019  0.9743589744  0.9932634731  0.9940119760  0.9866412214  0.9643312102  100.59880239  0.4166789071  5.3979983330  4200          0.2045459358 
0.9936377241  0.9658454700  1.0000000000  0.9584352078  0.9994669510  0.9722222222  0.9932634731  0.9940119760  0.9856870229  0.9668789809  107.78443113  0.3905146904  5.3979983330  4500          0.2034986440 
0.9936377241  0.9634004822  0.9975594875  0.9511002445  0.9989339019  0.9722222222  0.9932634731  0.9940119760  0.9850508906  0.9668789809  114.97005988  0.3816547852  5.3979983330  4800          0.2054696258 
0.9936377241  0.9718723247  0.9987797437  0.9731051345  0.9978678038  0.9743589744  0.9932634731  0.9940119760  0.9869592875  0.9681528662  119.76047904  0.3710407016  5.3979983330  5000          0.2171351111 
