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/d317f838f433fcd2f99b9231711dc7a1
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1946684382
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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 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    
0.1845969256  0.1777523240  0.1007067138  0.0918727915  0.3129411765  0.3163841808  0.1195734958  0.1250000000  0.1766012588  0.1925925926  0.0000000000  4.6652050018  2.1691374779  0             2.1009471416 
0.7931852396  0.8593179482  1.0000000000  0.9964664311  0.7637647059  0.7476459510  0.8804265042  0.8338414634  0.7997038134  0.7866666667  8.4805653710  1.7373028568  2.4361162186  300           0.6153660838 
0.8165156934  0.8739350612  1.0000000000  0.9964664311  0.8070588235  0.7777777778  0.9200304646  0.8475609756  0.8152536098  0.8177777778  16.961130742  1.2330850925  2.4361162186  600           0.6227767444 
0.8178123325  0.8772353893  1.0000000000  1.0000000000  0.8348235294  0.7871939736  0.9405940594  0.8445121951  0.8134024435  0.8222222222  25.441696113  1.0482297544  2.4361162186  900           0.6391247853 
0.8155901103  0.8711551782  1.0000000000  0.9964664311  0.8625882353  0.7740112994  0.9634424981  0.8429878049  0.8134024435  0.8177777778  33.922261484  0.9357910709  2.4361162186  1200          0.6451867890 
0.8157755011  0.8752928204  1.0000000000  1.0000000000  0.8884705882  0.7966101695  0.9706778370  0.8292682927  0.8122917438  0.8192592593  42.402826855  0.8812541085  2.4361162186  1500          0.6239807971 
0.8165162419  0.8740966573  1.0000000000  1.0000000000  0.9040000000  0.7777777778  0.9756283321  0.8445121951  0.8122917438  0.8207407407  50.883392226  0.8423347634  2.4361162186  1800          0.6328100912 
0.8150350346  0.8721540885  1.0000000000  1.0000000000  0.9251764706  0.7871939736  0.9859101295  0.8292682927  0.8108108108  0.8192592593  59.363957597  0.8086909389  2.4361162186  2100          0.6425603970 
0.8126276958  0.8741866088  1.0000000000  1.0000000000  0.9378823529  0.7871939736  0.9870525514  0.8353658537  0.8104405776  0.8148148148  67.844522968  0.7941053357  2.4361162186  2400          0.6344348049 
0.8105908644  0.8726622186  1.0000000000  1.0000000000  0.9444705882  0.7871939736  0.9908606245  0.8307926829  0.8093298778  0.8118518519  76.325088339  0.7853003389  2.4361162186  2700          0.6434103672 
0.8105905902  0.8686268428  1.0000000000  1.0000000000  0.9520000000  0.7796610169  0.9912414318  0.8262195122  0.8108108108  0.8103703704  84.805653710  0.7848390796  2.4361162186  3000          0.6501914374 
0.8092947738  0.8713770609  1.0000000000  1.0000000000  0.9675294118  0.7909604520  0.9946686976  0.8231707317  0.8082191781  0.8103703704  93.286219081  0.7751518933  2.4361162186  3300          0.6306017804 
0.8091093830  0.8761894643  1.0000000000  1.0000000000  0.9684705882  0.7947269303  0.9935262757  0.8338414634  0.8093298778  0.8088888889  101.76678445  0.7197985943  5.3953256607  3600          0.6297999072 
0.8091096572  0.8669828362  1.0000000000  1.0000000000  0.9689411765  0.7777777778  0.9961919269  0.8231707317  0.8078489448  0.8103703704  110.24734982  0.4068994921  5.3953256607  3900          0.6379817470 
0.8081837998  0.8739053964  1.0000000000  0.9964664311  0.9764705882  0.7853107345  0.9977151561  0.8399390244  0.8074787116  0.8088888889  118.72791519  0.3904687599  5.3953256607  4200          0.6405129123 
0.8079986832  0.8685368913  1.0000000000  1.0000000000  0.9764705882  0.7702448211  0.9946686976  0.8353658537  0.8071084783  0.8088888889  127.20848056  0.3777023765  5.3953256607  4500          0.6403477359 
0.8078135666  0.8670184929  1.0000000000  0.9929328622  0.9741176471  0.7834274953  0.9939070830  0.8246951220  0.8067382451  0.8088888889  135.68904593  0.3757635660  5.3953256607  4800          0.6371943506 
0.8072576682  0.8737857800  1.0000000000  0.9964664311  0.9788235294  0.7834274953  0.9980959634  0.8414634146  0.8085894113  0.8059259259  141.34275618  0.3700966635  5.3953256607  5000          0.6439986300 
