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: 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: 0
	output_dir: sweep/ablation3/outputs/cff59943417ca7f86047ca0ddb2acf7e
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1801907163
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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: 0.5
	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    
0.0615010053  0.0428520402  0.0266279989  0.0137130802  0.0603415073  0.0626605033  0.0510075567  0.0629722922  0.0552368812  0.0518707483  0.0000000000  4.3102407455  2.3339076042  0             1.4783687592 
0.3964821590  0.6918706400  0.8128130767  0.8006329114  0.3938888176  0.3990755008  0.6319269521  0.6083123426  0.6862120246  0.6666666667  3.0226700252  2.4338624982  2.5973362923  300           0.1647519779 
0.4722354156  0.7820702650  0.8871605589  0.8818565401  0.4611631788  0.4833076528  0.7638539043  0.7279596977  0.7539834289  0.7363945578  6.0453400504  2.0371889643  2.5973362923  600           0.1879667735 
0.4778204784  0.8147716087  0.9151067756  0.9082278481  0.4682244191  0.4874165383  0.7965994962  0.7707808564  0.7924367963  0.7653061224  9.0680100756  1.8838333587  2.5973362923  900           0.1892398620 
0.4872576214  0.8283447595  0.9317163195  0.9208860759  0.4752856593  0.4992295840  0.8243073048  0.7707808564  0.8202676864  0.7933673469  12.090680100  1.7407246208  2.5973362923  1200          0.1874728354 
0.4863587862  0.8366942864  0.9398892697  0.9219409283  0.4755424316  0.4971751412  0.8472921914  0.7896725441  0.8351391545  0.7984693878  15.113350125  1.6266241936  2.5973362923  1500          0.1882054218 
0.4844327296  0.8491950248  0.9451621408  0.9367088608  0.4757992040  0.4930662558  0.8652392947  0.8073047859  0.8461865307  0.8035714286  18.136020151  1.5243235894  2.5973362923  1800          0.1842015163 
0.4778844407  0.8564896723  0.9546533087  0.9367088608  0.4719476184  0.4838212635  0.8737405542  0.8249370277  0.8614828978  0.8078231293  21.158690176  1.4234657216  2.5973362923  2100          0.1857971255 
0.4749957186  0.8649034024  0.9630899025  0.9419831224  0.4666837848  0.4833076528  0.8844458438  0.8261964736  0.8727427236  0.8265306122  24.181360201  1.3766274790  2.5973362923  2400          0.1902940655 
0.4725560843  0.8729801380  0.9670445558  0.9472573840  0.4664270125  0.4786851567  0.8942065491  0.8400503778  0.8782664117  0.8316326531  27.204030226  1.3209595215  2.5973362923  2700          0.1914361262 
0.4674203072  0.8808845443  0.9736356446  0.9451476793  0.4612915650  0.4735490498  0.9045969773  0.8488664987  0.8918631825  0.8486394558  30.226700251  1.2949315516  2.5973362923  3000          0.1916085084 
0.4683833025  0.8818390972  0.9757447930  0.9472573840  0.4616767236  0.4750898819  0.9175062972  0.8564231738  0.8990864670  0.8418367347  33.249370277  1.2542117099  2.5973362923  3300          0.1871525979 
0.4669710215  0.8810315954  0.9767993673  0.9472573840  0.4593657722  0.4745762712  0.9228589421  0.8463476071  0.9022732101  0.8494897959  36.272040302  1.2385803648  2.5973362923  3600          0.1810799766 
0.4677414045  0.8950752805  0.9807540206  0.9578059072  0.4598793170  0.4756034926  0.9316750630  0.8702770781  0.9086466964  0.8571428571  39.294710327  1.0871727002  5.3950524330  3900          0.2051498326 
0.4663933166  0.8927502999  0.9815449512  0.9525316456  0.4576967518  0.4750898819  0.9363979849  0.8702770781  0.9103462928  0.8554421769  42.317380352  0.9074071121  5.3950524330  4200          0.2252368013 
0.4630550450  0.8948493763  0.9799630899  0.9525316456  0.4546154834  0.4714946071  0.9467884131  0.8765743073  0.9199065222  0.8554421769  45.340050377  0.8912276524  5.3950524330  4500          0.2242908367 
0.4597808676  0.8980607933  0.9844450303  0.9546413502  0.4532032353  0.4663585003  0.9458438287  0.8866498741  0.9213936690  0.8528911565  48.362720403  0.8822355870  5.3950524330  4800          0.2255685218 
0.4577907168  0.9034676728  0.9804903770  0.9567510549  0.4517909873  0.4637904468  0.9401763224  0.8803526448  0.9209687699  0.8732993197  50.377833753  0.8753629154  5.3950524330  5000          0.2229681492 
