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: OfficeHome
	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: 2
	output_dir: sweep/ablation3/outputs/9064a3047d3942a1f289b496fd940bfd
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 2043923600
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	trial_seed: 1
	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: 0.5439617198173775
	lambda2: 0.5509403872292429
	last_k_epoch: 0.38252238504986713
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.920147743151585
	weight_decay: 1e-06
	worst_case_p: 0.3
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    
0.0185492690  0.0102982127  0.0144181256  0.0226804124  0.0100229095  0.0183276060  0.0064752252  0.0033821871  0.0120481928  0.0091848450  0.0000000000  7.2242479324  2.1706647873  0             1.5902466774 
0.6651331921  0.7838490084  0.6416065911  0.6886597938  0.8078465063  0.7090492554  0.8879504505  0.8365276212  0.8866896156  0.8059701493  4.9433573635  4.4804381363  2.4395728111  300           0.3231946731 
0.7243812837  0.8477543546  0.7003089598  0.7484536082  0.9203894616  0.8018327606  0.9693130631  0.8883878241  0.9575444636  0.8530424799  9.8867147271  2.2588152715  2.4395728111  600           0.3099817753 
0.7300476708  0.8564554677  0.7075180227  0.7525773196  0.9438717068  0.8075601375  0.9791666667  0.9041713641  0.9776247849  0.8576349024  14.830072090  1.6653303281  2.4395728111  900           0.3030063017 
0.7349405965  0.8644575799  0.7152420185  0.7546391753  0.9636311569  0.8167239404  0.9876126126  0.9086809470  0.9842226047  0.8679678530  19.773429454  1.3731967723  2.4395728111  1200          0.3206884305 
0.7364853957  0.8694050910  0.7183316169  0.7546391753  0.9679266896  0.8167239404  0.9893018018  0.9131905299  0.9896729776  0.8783008037  24.716786817  1.2333248850  2.4395728111  1500          0.2995418191 
0.7390632462  0.8728190537  0.7173017508  0.7608247423  0.9765177549  0.8293241695  0.9926801802  0.9165727170  0.9896729776  0.8725602755  29.660144181  1.1647250094  2.4395728111  1800          0.3001718211 
0.7444732284  0.8724416124  0.7219361483  0.7670103093  0.9796678121  0.8224513173  0.9940878378  0.9165727170  0.9948364888  0.8783008037  34.603501544  1.1002086268  2.4395728111  2100          0.3147284587 
0.7436997671  0.8758513020  0.7224510814  0.7649484536  0.9808132875  0.8316151203  0.9935247748  0.9210822999  0.9934021801  0.8748564868  39.546858908  1.0497306410  2.4395728111  2400          0.3118879422 
0.7462776176  0.8712736736  0.7214212152  0.7711340206  0.9802405498  0.8213058419  0.9949324324  0.9199549042  0.9951233505  0.8725602755  44.490216271  1.0104497457  2.4395728111  2700          0.3038757213 
0.7480798833  0.8780836300  0.7250257467  0.7711340206  0.9833906071  0.8339060710  0.9949324324  0.9312288613  0.9959839357  0.8691159587  49.433573635  0.9849854398  2.4395728111  3000          0.3064790050 
0.7503992055  0.8697428661  0.7255406797  0.7752577320  0.9831042383  0.8213058419  0.9946509009  0.9199549042  0.9956970740  0.8679678530  54.376930999  0.8772095597  5.3998112679  3300          0.3108659045 
0.7501406772  0.8758470290  0.7270854789  0.7731958763  0.9839633448  0.8281786942  0.9954954955  0.9222096956  0.9965576592  0.8771526980  59.320288362  0.7730096614  5.3998112679  3600          0.3056096792 
0.7519440046  0.8746792009  0.7286302781  0.7752577320  0.9856815578  0.8178694158  0.9966216216  0.9267192785  0.9965576592  0.8794489093  64.263645726  0.7303884013  5.3998112679  3900          0.3152638690 
0.7514290716  0.8785130122  0.7276004119  0.7752577320  0.9851088202  0.8270332188  0.9952139640  0.9244644870  0.9974182444  0.8840413318  69.207003089  0.6945597674  5.3998112679  4200          0.3048194544 
0.7478213550  0.8799661299  0.7265705458  0.7690721649  0.9839633448  0.8293241695  0.9966216216  0.9368658399  0.9974182444  0.8737083812  74.150360453  0.6722085985  5.3998112679  4500          0.3062704452 
0.7475638885  0.8723414591  0.7260556128  0.7690721649  0.9862542955  0.8270332188  0.9974662162  0.9323562570  0.9959839357  0.8576349024  79.093717816  0.6451001793  5.3998112679  4800          0.3100685445 
0.7462754941  0.8777277753  0.7255406797  0.7670103093  0.9831042383  0.8258877434  0.9963400901  0.9278466742  0.9962707975  0.8794489093  82.389289392  0.6324182749  5.3998112679  5000          0.3087737465 
