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: 3
	output_dir: sweep/ablation3/outputs/f1c24b59d8dcb06bb8b27ca97d0d9990
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1072144866
	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: 0.8610090196552951
	lambda2: 0.5777772877463595
	last_k_epoch: 0.32350558703299503
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.866557071912062
	weight_decay: 0.0001
	worst_case_p: 0.25
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    
0.0097890367  0.0098793515  0.0092687951  0.0103092784  0.0177548683  0.0114547537  0.0059121622  0.0101465614  0.0106138841  0.0080367394  0.0000000000  9.9449186325  2.0088801384  0             1.5017747879 
0.6419463405  0.7588283593  0.6240988671  0.6597938144  0.7683276060  0.6781214204  0.8651463964  0.8015783540  0.8522662077  0.7967853042  4.9433573635  5.5894383931  2.2550172806  300           0.3059718068 
0.6991304529  0.8427856996  0.6869207003  0.7113402062  0.8960481100  0.7663230241  0.9493243243  0.8917700113  0.9457831325  0.8702640643  9.8867147271  3.0185305262  2.2550172806  600           0.3041836246 
0.7127836110  0.8553368395  0.6997940268  0.7257731959  0.9347079038  0.7961053837  0.9718468468  0.9007891770  0.9678714859  0.8691159587  14.830072090  2.2552644408  2.2550172806  900           0.3040640879 
0.7266963590  0.8599773637  0.7090628218  0.7443298969  0.9544673540  0.8144329897  0.9805743243  0.8906426156  0.9790590935  0.8748564868  19.773429454  1.9005028816  2.2550172806  1200          0.3174577967 
0.7377748518  0.8697810003  0.7167868177  0.7587628866  0.9630584192  0.8075601375  0.9876126126  0.9154453213  0.9819277108  0.8863375431  24.716786817  1.7543249599  2.2550172806  1500          0.3055613208 
0.7457626845  0.8720701976  0.7203913491  0.7711340206  0.9682130584  0.8167239404  0.9887387387  0.9154453213  0.9850831899  0.8840413318  29.660144181  1.6449743827  2.2550172806  1800          0.3095667998 
0.7439582954  0.8804006619  0.7209062822  0.7670103093  0.9736540664  0.8247422680  0.9912725225  0.9289740699  0.9893861159  0.8874856487  34.603501544  1.5559649118  2.2550172806  2100          0.3198681410 
0.7467936123  0.8698024763  0.7203913491  0.7731958763  0.9773768614  0.8155784651  0.9926801802  0.9109357384  0.9911072863  0.8828932262  39.546858908  1.4715075119  2.2550172806  2400          0.3101236033 
0.7485958780  0.8800041534  0.7239958805  0.7731958763  0.9779495991  0.8247422680  0.9938063063  0.9312288613  0.9936890419  0.8840413318  44.490216271  1.4611135610  2.2550172806  2700          0.3129101014 
0.7524621228  0.8777467317  0.7234809475  0.7814432990  0.9822451317  0.8281786942  0.9954954955  0.9244644870  0.9925415950  0.8805970149  49.433573635  1.3841877997  2.2550172806  3000          0.3110231002 
0.7519450664  0.8777080529  0.7265705458  0.7773195876  0.9819587629  0.8155784651  0.9935247748  0.9323562570  0.9934021801  0.8851894374  54.376930999  1.4101004676  2.2550172806  3300          0.3071914927 
0.7524589377  0.8777622919  0.7296601442  0.7752577320  0.9802405498  0.8258877434  0.9946509009  0.9222096956  0.9945496271  0.8851894374  59.320288362  1.2115108041  5.3968892097  3600          0.3210683918 
0.7519440046  0.8811031699  0.7286302781  0.7752577320  0.9833906071  0.8167239404  0.9946509009  0.9402480271  0.9959839357  0.8863375431  64.263645726  1.0323689395  5.3968892097  3900          0.3087350074 
0.7501406772  0.8807642967  0.7270854789  0.7731958763  0.9848224513  0.8316151203  0.9963400901  0.9312288613  0.9948364888  0.8794489093  69.207003089  0.9745322583  5.3968892097  4200          0.3086212452 
0.7485948163  0.8838016948  0.7260556128  0.7711340206  0.9853951890  0.8361970218  0.9954954955  0.9346110485  0.9948364888  0.8805970149  74.150360453  0.9284176997  5.3968892097  4500          0.2972248904 
0.7429273675  0.8792543098  0.7209062822  0.7649484536  0.9842497136  0.8224513173  0.9952139640  0.9289740699  0.9934021801  0.8863375431  79.093717816  0.8987289021  5.3968892097  4800          0.3069810518 
0.7462776176  0.8742825817  0.7214212152  0.7711340206  0.9833906071  0.8270332188  0.9963400901  0.9278466742  0.9954102123  0.8679678530  82.389289392  0.8705866590  5.3968892097  5000          0.2941602182 
