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: [0]
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/5a5b1714081345f3270960b7df0f3551
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 164136689
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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 normal transform
using augment 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    
0.1338339222  0.3601820846  0.1227915194  0.1448763251  0.3463529412  0.3540489642  0.4116527037  0.3887195122  0.3372824880  0.3377777778  0.0000000000  4.7246294022  1.7945408821  0             1.4534351826 
0.9430212009  0.8076094726  0.9567137809  0.9293286219  0.7501176471  0.7514124294  0.8434881950  0.8003048780  0.8937430581  0.8711111111  8.4805653710  1.8574311602  2.0919981003  300           0.6402636925 
0.9814487628  0.8107503225  0.9876325088  0.9752650177  0.7901176471  0.7457627119  0.8983244478  0.8094512195  0.9252128841  0.8770370370  16.961130742  1.4799555536  2.0919981003  600           0.6391125790 
0.9836572433  0.8264768241  0.9885159011  0.9787985866  0.8098823529  0.7627118644  0.9215536938  0.8307926829  0.9415031470  0.8859259259  25.441696113  1.3688688179  2.0919981003  900           0.6315684438 
0.9840989394  0.8210366744  0.9893992933  0.9787985866  0.8442352941  0.7570621469  0.9417364813  0.8201219512  0.9592743428  0.8859259259  33.922261484  1.2900779136  2.0919981003  1200          0.6337256416 
0.9823321550  0.8261793208  0.9858657244  0.9787985866  0.8536470588  0.7664783427  0.9550647372  0.8231707317  0.9748241392  0.8888888889  42.402826855  1.2185389187  2.0919981003  1500          0.6339349262 
0.9801236744  0.8159431887  0.9849823322  0.9752650177  0.8762352941  0.7419962335  0.9725818736  0.8125000000  0.9781562384  0.8933333333  50.883392226  1.1227678514  2.0919981003  1800          0.6439981214 
0.9814487628  0.8257284024  0.9840989399  0.9787985866  0.8992941176  0.7664783427  0.9786747906  0.8277439024  0.9859311366  0.8829629630  59.363957597  1.0349126248  2.0919981003  2100          0.6409053381 
0.9818904589  0.8244729097  0.9849823322  0.9787985866  0.9091764706  0.7627118644  0.9851485149  0.8277439024  0.9896334691  0.8829629630  67.844522968  0.9520643135  2.0919981003  2400          0.6412637369 
0.9818904589  0.8301687129  0.9849823322  0.9787985866  0.9275294118  0.7570621469  0.9889565880  0.8460365854  0.9929655683  0.8874074074  76.325088339  0.9346782502  2.0919981003  2700          0.6350608563 
0.9823321550  0.8293058679  0.9858657244  0.9787985866  0.9374117647  0.7608286252  0.9897182026  0.8307926829  0.9937060348  0.8962962963  84.805653710  0.9019929733  2.0919981003  3000          0.6348147488 
0.9827738511  0.8360925209  0.9867491166  0.9787985866  0.9444705882  0.7721280603  0.9935262757  0.8368902439  0.9970381340  0.8992592593  93.286219081  0.8983354070  2.0919981003  3300          0.6263557665 
0.9823321550  0.8282323960  0.9858657244  0.9787985866  0.9581176471  0.7608286252  0.9946686976  0.8216463415  0.9977786005  0.9022222222  101.76678445  0.8768733331  2.0919981003  3600          0.6282691002 
0.9836572433  0.8293979373  0.9849823322  0.9823321555  0.9618823529  0.7551789077  0.9965727342  0.8307926829  0.9966679008  0.9022222222  110.24734982  0.8805379272  2.0919981003  3900          0.6295648376 
0.9827738511  0.8290941821  0.9832155477  0.9823321555  0.9656470588  0.7645951036  0.9980959634  0.8323170732  0.9977786005  0.8903703704  118.72791519  0.6371669233  5.3999967575  4200          0.6369091328 
0.9867491161  0.8242765858  0.9840989399  0.9893992933  0.9755294118  0.7589453861  0.9980959634  0.8353658537  0.9974083673  0.8785185185  127.20848056  0.4987480144  5.3999967575  4500          0.6373469305 
0.9876325083  0.8251763046  0.9858657244  0.9893992933  0.9731764706  0.7740112994  0.9984767708  0.8170731707  0.9977786005  0.8844444444  135.68904593  0.4809479861  5.3999967575  4800          0.6419593692 
0.9876325083  0.8257918661  0.9858657244  0.9893992933  0.9755294118  0.7608286252  0.9973343488  0.8246951220  0.9977786005  0.8918518519  141.34275618  0.4667373742  5.3999967575  5000          0.6242205071 
