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: [3]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: TerraIncognita
	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/4e9372f3ca5049d7bffb7077cbd48dfe
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1539044857
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	trial_seed: 0
	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: 0.7419102898692578
	lambda2: 0.5215383105176172
	last_k_epoch: 0.23762453204831346
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.9748462276330736
	weight_decay: 1e-06
	worst_case_p: 0.3
using augment transform
using augment transform
using augment transform
using normal 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    
0.0773560220  0.0779219814  0.1447403111  0.1445147679  0.0151495699  0.0174627632  0.0834382872  0.0717884131  0.0781814319  0.0765306122  0.0000000000  4.6389527321  2.1692652702  0             1.4925765991 
0.2870057837  0.7178363733  0.7706301081  0.7647679325  0.7491333932  0.7539804828  0.6596347607  0.6347607053  0.2831952411  0.2908163265  3.0226700252  2.7686648528  2.4375615120  300           0.1591757298 
0.3479939775  0.7940925112  0.8713419457  0.8417721519  0.8217999743  0.8263995891  0.7556675063  0.7141057935  0.3575525813  0.3384353741  6.0453400504  2.3021181826  2.4375615120  600           0.1797612000 
0.3767903750  0.8335546318  0.9019245979  0.8839662447  0.8420849917  0.8459167951  0.7940806045  0.7707808564  0.3853834714  0.3681972789  9.0680100756  2.1451444360  2.4375615120  900           0.1811106769 
0.4020805420  0.8377740411  0.9132612708  0.8966244726  0.8589035820  0.8459167951  0.8107682620  0.7707808564  0.4087529212  0.3954081633  12.090680100  2.0099727321  2.4375615120  1200          0.1793302989 
0.4226962772  0.8612484604  0.9301344582  0.9092827004  0.8667351393  0.8633795583  0.8435138539  0.8110831234  0.4244741874  0.4209183673  15.113350125  1.9016852681  2.4375615120  1500          0.1861214503 
0.4341726172  0.8624759342  0.9396256262  0.9177215190  0.8806008473  0.8649203903  0.8554785894  0.8047858942  0.4346717655  0.4336734694  18.136020151  1.7827236752  2.4375615120  1800          0.1881486893 
0.4391665364  0.8755821569  0.9456894279  0.9272151899  0.8907433560  0.8834103749  0.8737405542  0.8161209068  0.4404079031  0.4379251701  21.158690176  1.7555243985  2.4375615120  2100          0.1825173521 
0.4407585530  0.8756019955  0.9501713683  0.9345991561  0.8990884581  0.8823831536  0.8916876574  0.8098236776  0.4478436371  0.4336734694  24.181360201  1.6629314605  2.4375615120  2400          0.1858516987 
0.4444769620  0.8864875284  0.9586079620  0.9293248945  0.9024264989  0.8900873138  0.9064861461  0.8400503778  0.4535797748  0.4353741497  27.204030226  1.6475967606  2.4375615120  2700          0.1859821113 
0.4471336652  0.8909336775  0.9554442394  0.9324894515  0.9069200154  0.8952234206  0.9102644836  0.8450881612  0.4554918207  0.4387755102  30.226700251  1.6397559265  2.4375615120  3000          0.1876413345 
0.4522335382  0.8904634695  0.9646717638  0.9388185654  0.9107716010  0.8988186954  0.9149874055  0.8337531486  0.4622902061  0.4421768707  33.249370277  1.6345291877  2.4375615120  3300          0.1865976826 
0.4563776592  0.9016706813  0.9678354864  0.9451476793  0.9155218898  0.9034411916  0.9165617128  0.8564231738  0.4663267474  0.4464285714  36.272040302  1.6126145407  2.4375615120  3600          0.1856792037 
0.4571223165  0.9049995392  0.9723174268  0.9398734177  0.9184747721  0.9111453518  0.9278967254  0.8639798489  0.4644147015  0.4498299320  39.294710327  1.5033210973  5.3968682289  3900          0.1928790593 
0.4523397630  0.9034989997  0.9728447139  0.9514767932  0.9195018616  0.8988186954  0.9288413098  0.8602015113  0.4625026556  0.4421768707  42.317380352  1.1680213881  5.3968682289  4200          0.2225708262 
0.4537214979  0.9059186113  0.9704719220  0.9419831224  0.9250224676  0.9054956343  0.9323047859  0.8702770781  0.4627151052  0.4447278912  45.340050377  1.1449500255  5.3968682289  4500          0.2220483375 
0.4531903741  0.9025430863  0.9715264962  0.9451476793  0.9264347156  0.9085772984  0.9329345088  0.8539042821  0.4616528574  0.4447278912  48.362720403  1.1248339003  5.3968682289  4800          0.2209501664 
0.4536155441  0.9075618336  0.9733720011  0.9462025316  0.9274618051  0.9162814587  0.9326196474  0.8602015113  0.4616528574  0.4455782313  50.377833753  1.1270432934  5.3968682289  5000          0.2199866927 
