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/b213f76e69a8fc9cc157eb8b31686284
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1108109227
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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: 0.5439617198173775
	lambda2: 0.5509403872292429
	last_k_epoch: 0.38252238504986713
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.920147743151585
	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    
0.1219818073  0.1207611240  0.2573161086  0.2837552743  0.0164334318  0.0231124807  0.0784005038  0.0554156171  0.1317187168  0.1122448980  0.0000000000  4.6839709282  2.1692652702  0             1.4965288639 
0.3628722201  0.7521955354  0.8286316900  0.8301687764  0.7949672615  0.7878787879  0.6275188917  0.6385390428  0.3660505630  0.3596938776  3.0226700252  2.5471821165  2.4375615120  300           0.1612932730 
0.3833784787  0.8281019897  0.8916424993  0.8691983122  0.8474772115  0.8418079096  0.7692065491  0.7732997481  0.3917569577  0.3750000000  6.0453400504  2.1401923811  2.4375615120  600           0.1785159214 
0.4044185709  0.8499972305  0.9140522014  0.8997890295  0.8644241880  0.8592706728  0.8066750630  0.7909319899  0.4100276184  0.3988095238  9.0680100756  1.9942948516  2.4375615120  900           0.1841806777 
0.4153640581  0.8639983456  0.9314526760  0.9156118143  0.8775195789  0.8715973292  0.8274559194  0.8047858942  0.4183131506  0.4124149660  12.090680100  1.8578103137  2.4375615120  1200          0.1809475072 
0.4300282252  0.8747489008  0.9430529924  0.9177215190  0.8857362948  0.8803287108  0.8416246851  0.8261964736  0.4314850223  0.4285714286  15.113350125  1.7397265569  2.4375615120  1500          0.1840325046 
0.4373590894  0.8879976194  0.9517532296  0.9314345992  0.8944665554  0.8849512070  0.8696473552  0.8476070529  0.4418950499  0.4328231293  18.136020151  1.6408058858  2.4375615120  1800          0.1836411762 
0.4439463801  0.8845490273  0.9578170314  0.9229957806  0.9037103608  0.8906009245  0.8844458438  0.8400503778  0.4508179307  0.4370748299  21.158690176  1.5657013814  2.4375615120  2100          0.1886201358 
0.4449034870  0.8979873701  0.9641444767  0.9388185654  0.9100012839  0.8936825886  0.8992443325  0.8614609572  0.4493307839  0.4404761905  24.181360201  1.5087049667  2.4375615120  2400          0.1792914136 
0.4471347492  0.9016266631  0.9675718429  0.9419831224  0.9142380280  0.9039548023  0.9134130982  0.8589420655  0.4520926280  0.4421768707  27.204030226  1.4959102591  2.4375615120  2700          0.1809405899 
0.4455411066  0.9039389278  0.9699446349  0.9430379747  0.9191167030  0.9085772984  0.9124685139  0.8602015113  0.4497556830  0.4413265306  30.226700251  1.4737000751  2.4375615120  3000          0.1809806617 
0.4437339306  0.9082841046  0.9720537833  0.9472573840  0.9233534472  0.9085772984  0.9184508816  0.8690176322  0.4503930317  0.4370748299  33.249370277  1.1521366062  5.3968682289  3300          0.2105653985 
0.4420332503  0.9116262396  0.9725810704  0.9472573840  0.9259211709  0.9060092450  0.9307304786  0.8816120907  0.4503930317  0.4336734694  36.272040302  0.9719240352  5.3968682289  3600          0.2230731018 
0.4423530085  0.9168665831  0.9736356446  0.9419831224  0.9281037360  0.9106317411  0.9323047859  0.8979848866  0.4476311876  0.4370748299  39.294710327  0.9517782718  5.3968682289  3900          0.2227225288 
0.4408653198  0.9190432546  0.9757447930  0.9535864979  0.9311850045  0.9219311762  0.9351385390  0.8816120907  0.4463564903  0.4353741497  42.317380352  0.9326107109  5.3968682289  4200          0.2207194193 
0.4384213371  0.9138881117  0.9767993673  0.9546413502  0.9350365901  0.9142270159  0.9363979849  0.8727959698  0.4440195454  0.4328231293  45.340050377  0.9281772351  5.3968682289  4500          0.2191097228 
0.4357651758  0.9214539970  0.9799630899  0.9556962025  0.9360636795  0.9131997946  0.9373425693  0.8954659950  0.4404079031  0.4311224490  48.362720403  0.9215969668  5.3968682289  4800          0.2177089254 
0.4373593604  0.9219932053  0.9770630108  0.9567510549  0.9392733342  0.9162814587  0.9458438287  0.8929471033  0.4410452518  0.4336734694  50.377833753  0.9214507765  5.3968682289  5000          0.2206790006 
