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: [0]
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: 3
	output_dir: sweep/ablation3/outputs/af6985112ee769fbbe081e5d81e73cd2
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 417977848
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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: 0.7010166027828918
	lambda2: 0.6269010951324223
	last_k_epoch: 0.38851977780027735
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.131347198605345
	weight_decay: 1e-06
	worst_case_p: 0.3
using normal transform
using augment 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    
0.0818720305  0.1311280674  0.0825204324  0.0812236287  0.2929772756  0.2865947612  0.0270780856  0.0277078086  0.0764818356  0.0790816327  0.0000000000  4.5612306595  2.1692652702  0             1.5542497635 
0.3559648240  0.6650727860  0.3627735302  0.3491561181  0.7550391578  0.7534668721  0.6108312343  0.6133501259  0.6320373911  0.6284013605  3.0226700252  2.6339477897  2.4363102913  300           0.1574822927 
0.2925517357  0.7466806447  0.2876351173  0.2974683544  0.8139684170  0.8140729327  0.7292191436  0.7040302267  0.7229657956  0.7219387755  6.0453400504  2.3066300845  2.4363102913  600           0.1741006525 
0.3476600520  0.7693215390  0.3461639863  0.3491561181  0.8409295160  0.8356445814  0.7748740554  0.7367758186  0.7595071171  0.7355442177  9.0680100756  2.1992145260  2.4363102913  900           0.1709956797 
0.3810162456  0.7846123006  0.3727919852  0.3892405063  0.8479907562  0.8418079096  0.7925062972  0.7569269521  0.7894625027  0.7551020408  12.090680100  2.1124516070  2.4363102913  1200          0.1737419581 
0.3964410621  0.8026848923  0.3909833905  0.4018987342  0.8613429195  0.8546481767  0.8158060453  0.7795969773  0.8111323561  0.7738095238  15.113350125  2.0397463775  2.4363102913  1500          0.1754513144 
0.4168760795  0.8111606930  0.4118112312  0.4219409283  0.8696880216  0.8685156651  0.8403652393  0.7732997481  0.8217548332  0.7916666667  18.136020151  1.9454123394  2.4363102913  1800          0.1775117151 
0.4383663664  0.8275414923  0.4294753493  0.4472573840  0.8773911927  0.8680020544  0.8576826196  0.8136020151  0.8385383471  0.8010204082  21.158690176  1.8905771780  2.4363102913  2100          0.1774889747 
0.4432451627  0.8328686652  0.4286844187  0.4578059072  0.8898446527  0.8721109399  0.8712216625  0.8161209068  0.8557467601  0.8103741497  24.181360201  1.8085869292  2.4363102913  2400          0.1804945652 
0.4482548074  0.8445955117  0.4355391511  0.4609704641  0.8947233278  0.8823831536  0.8775188917  0.8299748111  0.8676439346  0.8214285714  27.204030226  1.7405561896  2.4363102913  2700          0.1780801535 
0.4588019401  0.8556917377  0.4460848932  0.4715189873  0.8993452305  0.8957370313  0.8948362720  0.8337531486  0.8748672190  0.8375850340  30.226700251  1.7110766753  2.4363102913  3000          0.1774647872 
0.4499687686  0.8528843674  0.4368573688  0.4630801688  0.9021697265  0.8983050847  0.9052267003  0.8287153652  0.8799660081  0.8316326531  33.249370277  1.3072510978  5.3992714882  3300          0.2051359065 
0.4388940707  0.8552377332  0.4273662009  0.4504219409  0.9096161253  0.9003595275  0.9083753149  0.8362720403  0.8874017421  0.8290816327  36.272040302  1.1747962674  5.3992714882  3600          0.2140381384 
0.4312471562  0.8619145302  0.4215660427  0.4409282700  0.9111567595  0.8988186954  0.9130982368  0.8450881612  0.8878266412  0.8418367347  39.294710327  1.1522141989  5.3992714882  3900          0.2153224492 
0.4257096682  0.8672735666  0.4178750330  0.4335443038  0.9150083451  0.9013867488  0.9219143577  0.8526448363  0.8946250266  0.8477891156  42.317380352  1.1308756030  5.3992714882  4200          0.2128388683 
0.4217547368  0.8674900496  0.4120748748  0.4314345992  0.9191167030  0.9008731382  0.9238035264  0.8614609572  0.9024856597  0.8401360544  45.340050377  1.1289996692  5.3992714882  4500          0.2139921554 
0.4168766357  0.8746089919  0.4075929344  0.4261603376  0.9195018616  0.9060092450  0.9282115869  0.8564231738  0.9022732101  0.8613945578  48.362720403  1.1116847221  5.3992714882  4800          0.2147568758 
0.4159538833  0.8734672018  0.4057474295  0.4261603376  0.9225831301  0.9065228557  0.9326196474  0.8652392947  0.9084342469  0.8486394558  50.377833753  1.1016682214  5.3992714882  5000          0.2148438251 
