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: 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: 0
	output_dir: sweep/ablation3/outputs/02a4e1c1b42b8c0a20a4e218e8c6f154
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1378472316
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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: 0.5
	lambda2: 0.5
	last_k_epoch: 0.25
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3
	weight_decay: 0.0
	worst_case_p: 0.3333333333333333
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    
0.1332105904  0.1573538904  0.1749116608  0.1378091873  0.1214117647  0.1450094162  0.1892612338  0.1905487805  0.1369863014  0.1437037037  0.0000000000  3.4015989304  2.3337798119  0             1.7351381779 
0.6620378860  0.9109249255  0.9991166078  0.9929328622  0.6630588235  0.6610169492  0.9021325209  0.8628048780  0.9389115143  0.8770370370  8.4805653710  1.3525024426  2.5989427567  300           0.1649115411 
0.6507402234  0.9156453894  1.0000000000  0.9964664311  0.6555294118  0.6459510358  0.9364051790  0.8719512195  0.9666790078  0.8785185185  16.961130742  0.8299868895  2.5989427567  600           0.1877787137 
0.6540361136  0.9159347117  1.0000000000  0.9929328622  0.6545882353  0.6534839925  0.9539223153  0.8704268293  0.9774157719  0.8844444444  25.441696113  0.7086437281  2.5989427567  900           0.1923258416 
0.6521528744  0.9135413545  1.0000000000  0.9964664311  0.6545882353  0.6497175141  0.9706778370  0.8582317073  0.9825990374  0.8859259259  33.922261484  0.6432790174  2.5989427567  1200          0.1908357565 
0.6526234626  0.9133092439  1.0000000000  1.0000000000  0.6555294118  0.6497175141  0.9771515613  0.8658536585  0.9874120696  0.8740740741  42.402826855  0.6103780057  2.5989427567  1500          0.1871674244 
0.6516818430  0.9137887681  1.0000000000  1.0000000000  0.6555294118  0.6478342750  0.9821020564  0.8643292683  0.9903739356  0.8770370370  50.883392226  0.5874604585  2.5989427567  1800          0.1873850242 
0.6535650822  0.9122929837  1.0000000000  1.0000000000  0.6555294118  0.6516007533  0.9904798172  0.8628048780  0.9922251018  0.8740740741  59.363957597  0.5998437385  2.5989427567  2100          0.1887502090 
0.6535646391  0.9127439021  1.0000000000  1.0000000000  0.6574117647  0.6497175141  0.9927646611  0.8582317073  0.9944465013  0.8800000000  67.844522968  0.5825538632  2.5989427567  2400          0.1853036483 
0.6502691921  0.9126109118  1.0000000000  0.9964664311  0.6564705882  0.6440677966  0.9942878903  0.8643292683  0.9951869678  0.8770370370  76.325088339  0.5620442966  2.5989427567  2700          0.1884950527 
0.6486221333  0.9108401081  1.0000000000  1.0000000000  0.6531764706  0.6440677966  0.9927646611  0.8658536585  0.9933358016  0.8666666667  84.805653710  0.5445255464  2.5989427567  3000          0.1868729273 
0.6523886116  0.9110865216  1.0000000000  0.9964664311  0.6531764706  0.6516007533  0.9935262757  0.8597560976  0.9970381340  0.8770370370  93.286219081  0.5438547208  2.5989427567  3300          0.1837217816 
0.6507406666  0.9113053294  1.0000000000  1.0000000000  0.6536470588  0.6478342750  0.9965727342  0.8628048780  0.9970381340  0.8711111111  101.76678445  0.5379580058  2.5989427567  3600          0.1874267411 
0.6514469920  0.9166187408  1.0000000000  0.9964664311  0.6531764706  0.6497175141  0.9969535415  0.8704268293  0.9970381340  0.8829629630  110.24734982  0.4357958746  5.3940439224  3900          0.2036225367 
0.6509764038  0.9117562478  1.0000000000  1.0000000000  0.6522352941  0.6497175141  0.9973343488  0.8582317073  0.9985190670  0.8770370370  118.72791519  0.3015851896  5.3940439224  4200          0.2210542647 
0.6505053724  0.9125966089  1.0000000000  0.9964664311  0.6531764706  0.6478342750  0.9980959634  0.8628048780  0.9996297668  0.8785185185  127.20848056  0.2908352806  5.3940439224  4500          0.2195671892 
0.6516822861  0.9128297197  1.0000000000  1.0000000000  0.6536470588  0.6497175141  0.9977151561  0.8673780488  0.9985190670  0.8711111111  135.68904593  0.2824982698  5.3940439224  4800          0.2191219203 
0.6507406666  0.9151372593  1.0000000000  0.9964664311  0.6536470588  0.6478342750  0.9984767708  0.8704268293  0.9981488338  0.8785185185  141.34275618  0.2763856480  5.3940439224  5000          0.2195998454 
