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: [1]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: VLCS
	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/03adbe17354f7e32f650a5da8650dd94
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 635885311
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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 augment transform
using normal 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    
0.1652101473  0.3335217956  0.4832155477  0.4699646643  0.1872941176  0.1431261770  0.2817974105  0.2713414634  0.3024805628  0.2592592593  0.0000000000  4.1776390076  1.7945408821  0             1.6567144394 
0.6954598423  0.8988813607  1.0000000000  1.0000000000  0.6865882353  0.7043314501  0.8735719726  0.8018292683  0.9296556831  0.8948148148  8.4805653710  1.8085282993  2.0935831070  300           0.1509926351 
0.6672170153  0.9112656845  1.0000000000  0.9964664311  0.6621176471  0.6723163842  0.9211728865  0.8262195122  0.9533506109  0.9111111111  16.961130742  1.1785885259  2.0935831070  600           0.1700393303 
0.6554487645  0.9152449076  1.0000000000  0.9964664311  0.6536470588  0.6572504708  0.9432597106  0.8292682927  0.9681599408  0.9200000000  25.441696113  0.9878168470  2.0935831070  900           0.1706025052 
0.6490949371  0.9086063467  1.0000000000  0.9929328622  0.6447058824  0.6534839925  0.9649657273  0.8262195122  0.9781562384  0.9066666667  33.922261484  0.8743561866  2.0935831070  1200          0.1734036303 
0.6490953802  0.9132839019  1.0000000000  0.9964664311  0.6428235294  0.6553672316  0.9733434882  0.8307926829  0.9833395039  0.9125925926  42.402826855  0.7846676044  2.0935831070  1500          0.1745867904 
0.6486243489  0.9123391563  1.0000000000  0.9964664311  0.6437647059  0.6534839925  0.9836252856  0.8353658537  0.9874120696  0.9051851852  50.883392226  0.7654706142  2.0935831070  1800          0.1706153933 
0.6481537606  0.9103066360  1.0000000000  0.9964664311  0.6428235294  0.6534839925  0.9870525514  0.8292682927  0.9877823029  0.9051851852  59.363957597  0.7199993489  2.0935831070  2100          0.1715562431 
0.6476831724  0.9132982048  1.0000000000  0.9964664311  0.6418823529  0.6534839925  0.9897182026  0.8323170732  0.9914846353  0.9111111111  67.844522968  0.7225565905  2.0935831070  2400          0.1767784103 
0.6479184665  0.9099887079  1.0000000000  1.0000000000  0.6423529412  0.6534839925  0.9935262757  0.8277439024  0.9922251018  0.9022222222  76.325088339  0.7020512211  2.0935831070  2700          0.1733448688 
0.6479184665  0.9123248534  1.0000000000  0.9964664311  0.6423529412  0.6534839925  0.9931454684  0.8338414634  0.9911144021  0.9066666667  84.805653710  0.7376634262  2.0935831070  3000          0.1720201866 
0.6483894978  0.9129945796  1.0000000000  1.0000000000  0.6414117647  0.6553672316  0.9942878903  0.8323170732  0.9959274343  0.9066666667  93.286219081  0.6958314166  2.0935831070  3300          0.1711686754 
0.6481542037  0.9153879368  1.0000000000  0.9964664311  0.6409411765  0.6553672316  0.9969535415  0.8445121951  0.9959274343  0.9051851852  101.76678445  0.6811478567  2.0935831070  3600          0.1714968165 
0.6474478783  0.9139679310  1.0000000000  1.0000000000  0.6414117647  0.6534839925  0.9973343488  0.8307926829  0.9970381340  0.9111111111  110.24734982  0.6911876086  2.0935831070  3900          0.1706693618 
0.6469768469  0.9135027097  1.0000000000  1.0000000000  0.6423529412  0.6516007533  0.9973343488  0.8338414634  0.9959274343  0.9066666667  118.72791519  0.5654731463  5.3982496262  4200          0.2018064380 
0.6443877254  0.9138492437  1.0000000000  0.9964664311  0.6409411765  0.6478342750  0.9984767708  0.8384146341  0.9970381340  0.9066666667  127.20848056  0.3728902291  5.3982496262  4500          0.2179199211 
0.6455646391  0.9100602225  1.0000000000  1.0000000000  0.6414117647  0.6497175141  0.9984767708  0.8353658537  0.9977786005  0.8948148148  135.68904593  0.3474409707  5.3982496262  4800          0.2203259929 
0.6457999332  0.9174819328  1.0000000000  1.0000000000  0.6418823529  0.6497175141  0.9980959634  0.8368902439  0.9970381340  0.9155555556  141.34275618  0.3351919764  5.3982496262  5000          0.2197604084 
