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: 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/6ded1d275d86159afa47e43758fe2d77
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1396956284
	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    
0.2008882854  0.3063236731  0.5247349823  0.5759717314  0.1463529412  0.1280602637  0.2201066260  0.2149390244  0.2032580526  0.1985185185  0.0000000000  4.9970560074  1.7945408821  0             1.5919332504 
0.8111456658  0.8288894731  1.0000000000  0.9964664311  0.7534117647  0.7325800377  0.8332063976  0.7576219512  0.8134024435  0.8088888889  8.4805653710  2.0581224839  2.0945272446  300           0.6467757185 
0.8229972434  0.8565503802  1.0000000000  1.0000000000  0.7872941176  0.7495291902  0.9006092917  0.8201219512  0.8148833765  0.8311111111  16.961130742  1.4922864151  2.0945272446  600           0.6433447353 
0.8218862694  0.8551332913  1.0000000000  0.9964664311  0.8108235294  0.7457627119  0.9204112719  0.8231707317  0.8141429100  0.8296296296  25.441696113  1.4206827362  2.0945272446  900           0.6430028900 
0.8207758439  0.8578835094  1.0000000000  0.9964664311  0.8263529412  0.7570621469  0.9394516375  0.8201219512  0.8104405776  0.8311111111  33.922261484  1.2994952353  2.0945272446  1200          0.6303776558 
0.8111470370  0.8637244879  1.0000000000  1.0000000000  0.8343529412  0.7664783427  0.9531607007  0.8246951220  0.8059977786  0.8162962963  42.402826855  1.2281041022  2.0945272446  1500          0.6377441843 
0.8061472427  0.8651292619  1.0000000000  1.0000000000  0.8494117647  0.7645951036  0.9676313785  0.8307926829  0.8048870789  0.8074074074  50.883392226  1.1327671534  2.0945272446  1800          0.6557858817 
0.8055921671  0.8595694958  1.0000000000  1.0000000000  0.8625882353  0.7570621469  0.9767707540  0.8216463415  0.8022954461  0.8088888889  59.363957597  1.1098022223  2.0945272446  2100          0.6528575889 
0.8078138408  0.8626182763  1.0000000000  1.0000000000  0.8705882353  0.7570621469  0.9767707540  0.8307926829  0.8052573121  0.8103703704  67.844522968  1.0901009107  2.0945272446  2400          0.6441393304 
0.8065172017  0.8560125853  1.0000000000  1.0000000000  0.8776470588  0.7570621469  0.9836252856  0.8109756098  0.8071084783  0.8059259259  76.325088339  1.0572233230  2.0945272446  2700          0.6279592307 
0.8079986832  0.8535015997  1.0000000000  1.0000000000  0.8856470588  0.7495291902  0.9874333587  0.8109756098  0.8071084783  0.8088888889  84.805653710  1.0537722856  2.0945272446  3000          0.6377031883 
0.8091102057  0.8586431871  1.0000000000  1.0000000000  0.8917647059  0.7664783427  0.9881949733  0.8094512195  0.8048870789  0.8133333333  93.286219081  1.0351696150  2.0945272446  3300          0.6328424811 
0.8102206312  0.8588221331  1.0000000000  1.0000000000  0.8988235294  0.7532956685  0.9878141660  0.8231707317  0.8085894113  0.8118518519  101.76678445  0.7413274006  5.4002408981  3600          0.6252391020 
0.8118869550  0.8565983518  1.0000000000  0.9964664311  0.8978823529  0.7608286252  0.9912414318  0.8125000000  0.8104405776  0.8133333333  110.24734982  0.4823336322  5.4002408981  3900          0.6303428292 
0.8117015642  0.8558030175  1.0000000000  1.0000000000  0.9115294118  0.7457627119  0.9931454684  0.8216463415  0.8115512773  0.8118518519  118.72791519  0.4549303213  5.4002408981  4200          0.6459943144 
0.8124423049  0.8566699965  1.0000000000  1.0000000000  0.9054117647  0.7514124294  0.9904798172  0.8185975610  0.8115512773  0.8133333333  127.20848056  0.4508309435  5.4002408981  4500          0.6507937082 
0.8120720717  0.8494365591  1.0000000000  1.0000000000  0.9167058824  0.7495291902  0.9916222391  0.7987804878  0.8108108108  0.8133333333  135.68904593  0.4375227986  5.4002408981  4800          0.6477684975 
0.8135532789  0.8498547377  1.0000000000  1.0000000000  0.9157647059  0.7401129944  0.9931454684  0.8094512195  0.8122917438  0.8148148148  141.34275618  0.4305955301  5.4002408981  5000          0.6257624078 
