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: 4
	output_dir: sweep/ablation3/outputs/b88d19bcc793dd2bbc736461ec77c1fb
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 511422982
	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: 0.5122476832929141
	lambda2: 0.9892716333303577
	last_k_epoch: 0.2899069879248226
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.19589595208549
	weight_decay: 0.0001
	worst_case_p: 0.3
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    
0.1663892765  0.2009998238  0.2641342756  0.2508833922  0.1783529412  0.1544256121  0.2056359482  0.1935975610  0.1614216957  0.1585185185  0.0000000000  5.8580598831  2.1691374779  0             1.6563358307 
0.6540352273  0.9077331158  1.0000000000  0.9929328622  0.6583529412  0.6497175141  0.8796648896  0.8384146341  0.9178082192  0.8918518519  8.4805653710  1.6912438051  2.4361162186  300           0.1527908357 
0.6575677409  0.9143573737  1.0000000000  0.9964664311  0.6522352941  0.6629001883  0.9135567403  0.8399390244  0.9411329137  0.9066666667  16.961130742  1.0154694176  2.4361162186  600           0.1752064586 
0.6561564193  0.9066596439  1.0000000000  0.9929328622  0.6475294118  0.6647834275  0.9310738766  0.8292682927  0.9529803776  0.8977777778  25.441696113  0.8842523674  2.4361162186  900           0.1792735879 
0.6547446546  0.9104682322  1.0000000000  1.0000000000  0.6447058824  0.6647834275  0.9436405179  0.8262195122  0.9648278415  0.9051851852  33.922261484  0.7924255949  2.4361162186  1200          0.1804984474 
0.6507437684  0.9088537604  1.0000000000  0.9964664311  0.6404705882  0.6610169492  0.9592536177  0.8323170732  0.9737134395  0.8977777778  42.402826855  0.7555985095  2.4361162186  1500          0.1842698367 
0.6530975958  0.9122962476  1.0000000000  0.9964664311  0.6414117647  0.6647834275  0.9695354151  0.8307926829  0.9803776379  0.9096296296  50.883392226  0.7272204441  2.4361162186  1800          0.1800468159 
0.6542749526  0.9146896048  1.0000000000  0.9929328622  0.6400000000  0.6685499058  0.9760091394  0.8429878049  0.9829692706  0.9081481481  59.363957597  0.7034611434  2.4361162186  2100          0.1826749007 
0.6554518663  0.9144145854  1.0000000000  0.9964664311  0.6404705882  0.6704331450  0.9843869002  0.8460365854  0.9844502036  0.9007407407  67.844522968  0.6798734494  2.4361162186  2400          0.1837573711 
0.6566287800  0.9120212282  1.0000000000  1.0000000000  0.6409411765  0.6723163842  0.9881949733  0.8338414634  0.9911144021  0.9022222222  76.325088339  0.6758306507  2.4361162186  2700          0.1825182978 
0.6566287800  0.9155066242  1.0000000000  1.0000000000  0.6409411765  0.6723163842  0.9874333587  0.8368902439  0.9900037023  0.9096296296  84.805653710  0.6522348148  2.4361162186  3000          0.1801259629 
0.6575703996  0.9085644381  0.9982332155  1.0000000000  0.6409411765  0.6741996234  0.9889565880  0.8338414634  0.9911144021  0.8918518519  93.286219081  0.6509938580  2.4361162186  3300          0.1847238191 
0.6578056937  0.9155352300  1.0000000000  1.0000000000  0.6414117647  0.6741996234  0.9908606245  0.8399390244  0.9925953351  0.9066666667  101.76678445  0.6166021115  5.3953256607  3600          0.1894955532 
0.6596889329  0.9155638359  1.0000000000  1.0000000000  0.6414117647  0.6779661017  0.9927646611  0.8429878049  0.9933358016  0.9037037037  110.24734982  0.3683723568  5.3953256607  3900          0.2182615519 
0.6582762819  0.9119783195  1.0000000000  1.0000000000  0.6423529412  0.6741996234  0.9912414318  0.8292682927  0.9940762680  0.9066666667  118.72791519  0.3491434021  5.3953256607  4200          0.2198006638 
0.6582762819  0.9135742243  1.0000000000  1.0000000000  0.6423529412  0.6741996234  0.9946686976  0.8414634146  0.9948167345  0.8992592593  127.20848056  0.3367828635  5.3953256607  4500          0.2188243628 
0.6559224545  0.9115274011  1.0000000000  1.0000000000  0.6414117647  0.6704331450  0.9946686976  0.8338414634  0.9940762680  0.9007407407  135.68904593  0.3264298032  5.3953256607  4800          0.2232189353 
0.6549808349  0.9140108398  1.0000000000  1.0000000000  0.6414117647  0.6685499058  0.9950495050  0.8353658537  0.9959274343  0.9066666667  141.34275618  0.3243044025  5.3953256607  5000          0.2205264056 
