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: [1]
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: 4
	output_dir: sweep/ablation3/outputs/d848baf6969d93897fc8fb47f2fec886
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1931876827
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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 normal 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    
0.0180412371  0.0179479578  0.0144181256  0.0164948454  0.0166093929  0.0194730813  0.0244932432  0.0293122886  0.0183591509  0.0080367394  0.0000000000  11.990471839  2.1706647873  0             1.5234630108 
0.5110252002  0.8003716883  0.8717816684  0.7402061856  0.5077319588  0.5143184422  0.8918918919  0.8342728298  0.8760757315  0.8266360505  4.9433573635  6.2554910556  2.4395728111  300           0.3015832059 
0.5621420387  0.8561779582  0.9552008239  0.8144329897  0.5572737686  0.5670103093  0.9512950450  0.8861330327  0.9460699943  0.8679678530  9.8867147271  2.9734773922  2.4395728111  600           0.3108983866 
0.5668671246  0.8648410478  0.9742533471  0.8247422680  0.5621420389  0.5715922108  0.9673423423  0.9075535513  0.9635685600  0.8622273249  14.830072090  2.2703163362  2.4395728111  900           0.3048429251 
0.5813287511  0.8633457443  0.9850669413  0.8144329897  0.5693012600  0.5933562428  0.9774774775  0.9030439684  0.9744693058  0.8725602755  19.773429454  1.9777968637  2.4395728111  1200          0.3005575538 
0.5841924396  0.8690300585  0.9891864058  0.8247422680  0.5738831615  0.5945017182  0.9808558559  0.9109357384  0.9790590935  0.8714121699  24.716786817  1.8095667096  2.4395728111  1500          0.2907398891 
0.5846219928  0.8711355162  0.9922760041  0.8288659794  0.5747422680  0.5945017182  0.9864864865  0.9165727170  0.9853700516  0.8679678530  29.660144181  1.6833018871  2.4395728111  1800          0.3050773780 
0.5829037798  0.8681163085  0.9922760041  0.8185567010  0.5747422680  0.5910652921  0.9873310811  0.9109357384  0.9868043603  0.8748564868  34.603501544  1.6023319439  2.4395728111  2100          0.2941095972 
0.5813287511  0.8768038416  0.9907312049  0.8412371134  0.5750286369  0.5876288660  0.9878941441  0.9143179256  0.9908204246  0.8748564868  39.546858908  1.5313875759  2.4395728111  2400          0.2973608677 
0.5846219928  0.8741259160  0.9943357364  0.8309278351  0.5770332188  0.5922107675  0.9912725225  0.9154453213  0.9916810098  0.8760045924  44.490216271  1.4738830471  2.4395728111  2700          0.2880845094 
0.5854810994  0.8800919215  0.9922760041  0.8453608247  0.5787514318  0.5922107675  0.9921171171  0.9143179256  0.9934021801  0.8805970149  49.433573635  1.4191613321  2.4395728111  3000          0.2946113404 
0.5844788084  0.8813686509  0.9958805355  0.8412371134  0.5778923253  0.5910652921  0.9923986486  0.9188275085  0.9942627653  0.8840413318  54.376930999  1.3773318402  2.4395728111  3300          0.2993192792 
0.5851947305  0.8717722961  0.9943357364  0.8329896907  0.5770332188  0.5933562428  0.9929617117  0.9120631342  0.9948364888  0.8702640643  59.320288362  1.3512174586  5.3996052742  3600          0.2988251177 
0.5839060707  0.8745224245  0.9958805355  0.8309278351  0.5767468499  0.5910652921  0.9935247748  0.9131905299  0.9936890419  0.8794489093  64.263645726  1.1492352959  5.3996052742  3900          0.3044766450 
0.5850515461  0.8752592275  0.9943357364  0.8412371134  0.5767468499  0.5933562428  0.9918355856  0.9165727170  0.9942627653  0.8679678530  69.207003089  1.0550566006  5.3996052742  4200          0.2929859082 
0.5846219928  0.8745066429  0.9948506694  0.8515463918  0.5770332188  0.5922107675  0.9954954955  0.9131905299  0.9948364888  0.8587830080  74.150360453  0.9868749108  5.3996052742  4500          0.2991829673 
0.5837628863  0.8806744624  0.9958805355  0.8391752577  0.5776059565  0.5899198167  0.9943693694  0.9199549042  0.9956970740  0.8828932262  79.093717816  0.9485192688  5.3996052742  4800          0.3032519380 
0.5837628863  0.8830409014  0.9943357364  0.8474226804  0.5776059565  0.5899198167  0.9952139640  0.9199549042  0.9948364888  0.8817451206  82.389289392  0.9178064618  5.3996052742  5000          0.2975891984 
