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: 4
	output_dir: sweep/ablation3/outputs/7fbd94b6f5752c16ecf4320af21a0c9e
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1010103620
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	trial_seed: 2
	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: 0.5122476832929141
	lambda2: 0.9892716333303577
	last_k_epoch: 0.2899069879248226
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.19589595208549
	weight_decay: 0.0001
	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    
0.1365448983  0.1184143734  0.0253097812  0.0232067511  0.1995121325  0.1997945557  0.1391687657  0.1322418136  0.1285319737  0.1445578231  0.0000000000  4.3740782738  2.1692652702  0             1.7024774551 
0.3089981051  0.7101640977  0.7959398893  0.7837552743  0.7587623572  0.7308680021  0.6690806045  0.6158690176  0.3152751222  0.3027210884  3.0226700252  2.6339424102  2.4374394417  300           0.1678260946 
0.3624448822  0.7920036018  0.8781966781  0.8523206751  0.8265502632  0.8032871084  0.7556675063  0.7204030227  0.3728489484  0.3520408163  6.0453400504  2.1851293341  2.4374394417  600           0.1843984238 
0.3985732277  0.8153516382  0.9053519641  0.8765822785  0.8482475286  0.8263995891  0.7899874055  0.7430730479  0.4076906735  0.3894557823  9.0680100756  2.0146095689  2.4374394417  900           0.1887095324 
0.4183383517  0.8374414597  0.9298708147  0.8945147679  0.8630119399  0.8382126348  0.8224181360  0.7795969773  0.4242617378  0.4124149660  12.090680100  1.8803685145  2.4374394417  1200          0.1839932887 
0.4301341790  0.8494686505  0.9448984972  0.9050632911  0.8743099243  0.8561890087  0.8441435768  0.7871536524  0.4325472700  0.4277210884  15.113350125  1.7708998422  2.4374394417  1500          0.1834741187 
0.4349148357  0.8553256104  0.9472712892  0.9008438819  0.8813711645  0.8628659476  0.8579974811  0.8022670025  0.4404079031  0.4294217687  18.136020151  1.6853771885  2.4374394417  1800          0.1826798741 
0.4470298793  0.8665632889  0.9541260216  0.9208860759  0.8898446527  0.8664612224  0.8781486146  0.8123425693  0.4476311876  0.4464285714  21.158690176  1.6024635466  2.4374394417  2100          0.1857278228 
0.4548943061  0.8753603737  0.9591352491  0.9219409283  0.8931826935  0.8741653826  0.8797229219  0.8299748111  0.4514552794  0.4583333333  24.181360201  1.5527777421  2.4374394417  2400          0.1847276417 
0.4580821332  0.8772620335  0.9649354073  0.9240506329  0.8997303890  0.8777606574  0.8942065491  0.8299748111  0.4544295730  0.4617346939  27.204030226  1.4798452063  2.4374394417  2700          0.1834343060 
0.4585078452  0.8839764291  0.9683627735  0.9251054852  0.9055077674  0.8880328711  0.9020780856  0.8387909320  0.4527299766  0.4642857143  30.226700251  1.4507092877  2.4374394417  3000          0.1815794786 
0.4581886290  0.8910813169  0.9736356446  0.9335443038  0.9083322634  0.8895737031  0.9108942065  0.8501259446  0.4537922243  0.4625850340  33.249370277  1.4218891482  2.4374394417  3300          0.1807788754 
0.4577631879  0.8968657378  0.9715264962  0.9419831224  0.9128257799  0.8947098100  0.9228589421  0.8539042821  0.4546420225  0.4608843537  36.272040302  1.3569983196  5.3972420692  3600          0.1878388929 
0.4560630496  0.8941316244  0.9728447139  0.9388185654  0.9179612274  0.8947098100  0.9234886650  0.8488664987  0.4529424262  0.4591836735  39.294710327  1.0829845337  5.3972420692  3900          0.2182412767 
0.4550005309  0.8919039447  0.9754811495  0.9367088608  0.9214276544  0.8926553672  0.9260075567  0.8463476071  0.4516677289  0.4583333333  42.317380352  1.0593866014  5.3972420692  4200          0.2226754204 
0.4508553260  0.8969540485  0.9783812286  0.9324894515  0.9237386057  0.9044684129  0.9348236776  0.8539042821  0.4510303803  0.4506802721  45.340050377  1.0426359979  5.3972420692  4500          0.2180719837 
0.4496857696  0.9073492607  0.9757447930  0.9419831224  0.9273334189  0.9060092450  0.9316750630  0.8740554156  0.4520926280  0.4472789116  48.362720403  1.0247330556  5.3972420692  4800          0.2180345909 
0.4481983518  0.9024570833  0.9815449512  0.9409282700  0.9272050327  0.9049820236  0.9357682620  0.8614609572  0.4499681326  0.4464285714  50.377833753  1.0200346333  5.3972420692  5000          0.2178770053 
