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: PACS
	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/a9e0d45b4a63820c9403a95e90499c96
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 888547305
	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: 0.8001163740830898
	lambda2: 0.7340462818445315
	last_k_epoch: 0.3149495809125332
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.8284464949429635
	weight_decay: 1e-06
	worst_case_p: 0.2
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    
0.1364844685  0.1594786908  0.1409395973  0.1320293399  0.2084221748  0.1923076923  0.0928143713  0.1077844311  0.1755725191  0.1783439490  0.0000000000  10.319780349  1.7945718765  0             1.5232450962 
0.8888582246  0.9556982770  0.8852959121  0.8924205379  0.9717484009  0.9508547009  0.9992514970  0.9850299401  0.9341603053  0.9312101911  7.1856287425  3.7064371932  2.0936598778  300           0.1465720336 
0.9206117388  0.9667658365  0.9194630872  0.9217603912  0.9904051173  0.9636752137  1.0000000000  0.9850299401  0.9627862595  0.9515923567  14.371257485  1.3197268335  2.0936598778  600           0.1657027062 
0.9212173916  0.9715972375  0.9255643685  0.9168704156  0.9914712154  0.9658119658  1.0000000000  0.9910179641  0.9653307888  0.9579617834  21.556886227  1.1207445912  2.0936598778  900           0.1663272500 
0.9221325838  0.9708751148  0.9273947529  0.9168704156  0.9957356077  0.9658119658  1.0000000000  0.9850299401  0.9681933842  0.9617834395  28.742514970  1.0179772198  2.0936598778  1200          0.1681357837 
0.9221325838  0.9697635864  0.9273947529  0.9168704156  0.9962686567  0.9722222222  1.0000000000  0.9880239521  0.9713740458  0.9490445860  35.928143712  0.9627357848  2.0936598778  1500          0.1667678865 
0.9233573153  0.9785672595  0.9249542404  0.9217603912  0.9968017058  0.9786324786  1.0000000000  0.9940119760  0.9751908397  0.9630573248  43.113772455  0.9314009635  2.0936598778  1800          0.1653856039 
0.9242725075  0.9703252211  0.9267846248  0.9217603912  0.9978678038  0.9700854701  1.0000000000  0.9880239521  0.9799618321  0.9528662420  50.299401197  0.9144218361  2.0936598778  2100          0.1652982759 
0.9245798092  0.9706011024  0.9249542404  0.9242053790  0.9978678038  0.9700854701  1.0000000000  0.9850299401  0.9805979644  0.9566878981  57.485029940  0.8680700030  2.0936598778  2400          0.1638840771 
0.9239674435  0.9742993622  0.9261744966  0.9217603912  0.9978678038  0.9786324786  1.0000000000  0.9850299401  0.9796437659  0.9592356688  64.670658682  0.8546517141  2.0936598778  2700          0.1635777203 
0.9254927638  0.9760058789  0.9292251373  0.9217603912  0.9962686567  0.9722222222  1.0000000000  0.9940119760  0.9796437659  0.9617834395  71.856287425  0.8427877407  2.0936598778  3000          0.1642195431 
0.9267152577  0.9747085118  0.9292251373  0.9242053790  0.9973347548  0.9679487179  1.0000000000  0.9880239521  0.9828244275  0.9681528662  79.041916167  0.8289968129  2.0936598778  3300          0.1642909877 
0.9254927638  0.9714602313  0.9292251373  0.9217603912  0.9978678038  0.9679487179  1.0000000000  0.9910179641  0.9809160305  0.9554140127  86.227544910  0.6198794076  5.4008765221  3600          0.1960844604 
0.9270180841  0.9742956242  0.9322757779  0.9217603912  0.9994669510  0.9700854701  1.0000000000  0.9910179641  0.9837786260  0.9617834395  93.413173652  0.4143825178  5.4008765221  3900          0.2088848972 
0.9251854621  0.9754325034  0.9310555217  0.9193154034  0.9984008529  0.9722222222  1.0000000000  0.9910179641  0.9821882952  0.9630573248  100.59880239  0.3838559645  5.4008765221  4200          0.2076857503 
0.9251854621  0.9737241177  0.9310555217  0.9193154034  0.9984008529  0.9743589744  1.0000000000  0.9850299401  0.9831424936  0.9617834395  107.78443113  0.3575299591  5.4008765221  4500          0.2090674400 
0.9257955902  0.9721724820  0.9322757779  0.9193154034  0.9978678038  0.9700854701  1.0000000000  0.9910179641  0.9860050891  0.9554140127  114.97005988  0.3426796988  5.4008765221  4800          0.2092321348 
0.9273231482  0.9711589991  0.9328859060  0.9217603912  0.9968017058  0.9594017094  1.0000000000  0.9910179641  0.9847328244  0.9630573248  119.76047904  0.3350639425  5.4008765221  5000          0.2097664523 
