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: 2
	output_dir: sweep/ablation3/outputs/6629f8b022d0c225d82db797008e3f5a
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 175453633
	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: 0.8194577311903198
	lambda2: 0.5954971958468116
	last_k_epoch: 0.2502561813215683
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.3092434210820203
	weight_decay: 1e-06
	worst_case_p: 0.25
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    
0.0176116838  0.0142175853  0.0144181256  0.0164948454  0.0180412371  0.0171821306  0.0219594595  0.0135287486  0.0137693632  0.0126291619  0.0000000000  11.047690391  2.0088801384  0             1.5919759274 
0.4978522334  0.7915594723  0.8501544799  0.7525773196  0.4928407789  0.5028636884  0.8710585586  0.8218714769  0.8620195066  0.8002296211  4.9433573635  6.2672709155  2.2550172806  300           0.3104445863 
0.5296391750  0.8392745565  0.9531410917  0.7979381443  0.5254868270  0.5337915235  0.9498873874  0.8737316798  0.9383247275  0.8461538462  9.8867147271  2.9684720540  2.2550172806  600           0.3076143018 
0.5493986252  0.8517200754  0.9773429454  0.8206185567  0.5386597938  0.5601374570  0.9639639640  0.8883878241  0.9595524957  0.8461538462  14.830072090  2.2397081526  2.2550172806  900           0.3265569496 
0.5564146618  0.8611367370  0.9845520082  0.8103092784  0.5504009164  0.5624284078  0.9729729730  0.9143179256  0.9693057946  0.8587830080  19.773429454  1.9378793736  2.2550172806  1200          0.3098379985 
0.5608533789  0.8734078479  0.9840370752  0.8412371134  0.5558419244  0.5658648339  0.9786036036  0.9064261556  0.9787722318  0.8725602755  24.716786817  1.7746516490  2.2550172806  1500          0.3085022052 
0.5605670100  0.8622481440  0.9902162719  0.8123711340  0.5552691867  0.5658648339  0.9831081081  0.9075535513  0.9833620195  0.8668197474  29.660144181  1.6780391983  2.2550172806  1800          0.3178903286 
0.5650057271  0.8672579921  0.9927909372  0.8309278351  0.5561282932  0.5738831615  0.9862049550  0.9120631342  0.9868043603  0.8587830080  34.603501544  1.5967712402  2.2550172806  2100          0.3162582294 
0.5684421532  0.8646490995  0.9953656025  0.8206185567  0.5595647194  0.5773195876  0.9884572072  0.9019165727  0.9896729776  0.8714121699  39.546858908  1.5391642288  2.2550172806  2400          0.2999276034 
0.5694444442  0.8764211398  0.9927909372  0.8412371134  0.5627147766  0.5761741123  0.9907094595  0.9143179256  0.9893861159  0.8737083812  44.490216271  1.4868522123  2.2550172806  2700          0.2997479367 
0.5697308130  0.8695611067  0.9943357364  0.8309278351  0.5655784651  0.5738831615  0.9935247748  0.9109357384  0.9916810098  0.8668197474  49.433573635  1.4570890927  2.2550172806  3000          0.3091387304 
0.5710194728  0.8761522677  0.9933058702  0.8474226804  0.5693012600  0.5727376861  0.9940878378  0.9199549042  0.9931153184  0.8610792193  54.376930999  1.4061173987  2.2550172806  3300          0.3070602338 
0.5714490261  0.8769176714  0.9922760041  0.8474226804  0.5701603666  0.5727376861  0.9915540541  0.9199549042  0.9913941480  0.8633754305  59.320288362  1.3712296653  2.2550172806  3600          0.3172957277 
0.5727376859  0.8708585461  0.9943357364  0.8268041237  0.5704467354  0.5750286369  0.9935247748  0.9120631342  0.9936890419  0.8737083812  64.263645726  1.2593318250  5.3961720467  3900          0.3126663597 
0.5733104235  0.8715150484  0.9943357364  0.8412371134  0.5693012600  0.5773195876  0.9938063063  0.9030439684  0.9934021801  0.8702640643  69.207003089  1.0439841100  5.3961720467  4200          0.3204281346 
0.5734536080  0.8705758674  0.9953656025  0.8329896907  0.5707331042  0.5761741123  0.9932432432  0.9199549042  0.9948364888  0.8587830080  74.150360453  0.9777738764  5.3961720467  4500          0.3076668771 
0.5740263456  0.8792860853  0.9943357364  0.8350515464  0.5718785796  0.5761741123  0.9940878378  0.9222096956  0.9968445209  0.8805970149  79.093717816  0.9387891916  5.3961720467  4800          0.3090490190 
0.5730240547  0.8752156255  0.9938208033  0.8432989691  0.5721649485  0.5738831615  0.9926801802  0.9109357384  0.9959839357  0.8714121699  82.389289392  0.8975953716  5.3961720467  5000          0.3226098096 
