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: 1
	output_dir: sweep/ablation3/outputs/2289afff1ad59d8f827eac3a99646d3a
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 213005656
	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: 0.6880433961757358
	lambda2: 0.9840350138898164
	last_k_epoch: 0.33648211095401626
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3.599417945900826
	weight_decay: 0.0001
	worst_case_p: 0.25
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    
0.1322292351  0.1388167592  0.1153142160  0.1491442543  0.1855010661  0.1645299145  0.0546407186  0.0748502994  0.1844783715  0.1770700637  0.0000000000  8.8420085907  2.0074062347  0             1.4782896042 
0.9123638209  0.9653629479  0.9151921904  0.9095354523  0.9706823028  0.9594017094  1.0000000000  0.9940119760  0.9548346056  0.9426751592  7.1856287425  3.2258555335  2.2566514015  300           0.1495722683 
0.9291624831  0.9735815045  0.9267846248  0.9315403423  0.9882729211  0.9636752137  0.9992514970  0.9940119760  0.9685114504  0.9630573248  14.371257485  1.2612668310  2.2566514015  600           0.1705268017 
0.9288574190  0.9687482346  0.9261744966  0.9315403423  0.9941364606  0.9572649573  1.0000000000  0.9910179641  0.9713740458  0.9579617834  21.556886227  1.1093065987  2.2566514015  900           0.1708802962 
0.9312979315  0.9740216118  0.9310555217  0.9315403423  0.9946695096  0.9743589744  1.0000000000  0.9910179641  0.9770992366  0.9566878981  28.742514970  1.0211920557  2.2566514015  1200          0.1708078671 
0.9300754376  0.9728692538  0.9310555217  0.9290953545  0.9962686567  0.9615384615  1.0000000000  0.9940119760  0.9796437659  0.9630573248  35.928143712  0.9580803325  2.2566514015  1500          0.1711372654 
0.9300754376  0.9720237349  0.9310555217  0.9290953545  0.9978678038  0.9700854701  1.0000000000  0.9880239521  0.9828244275  0.9579617834  43.113772455  0.8790077538  2.2566514015  1800          0.1706005200 
0.9325181878  0.9734444983  0.9334960342  0.9315403423  0.9968017058  0.9658119658  1.0000000000  0.9940119760  0.9850508906  0.9605095541  50.299401197  0.8571593626  2.2566514015  2100          0.1710795530 
0.9343508098  0.9757083847  0.9347162904  0.9339853301  0.9973347548  0.9722222222  1.0000000000  0.9880239521  0.9847328244  0.9668789809  57.485029940  0.8306753194  2.2566514015  2400          0.1730356558 
0.9364907335  0.9742937552  0.9341061623  0.9388753056  0.9973347548  0.9658119658  1.0000000000  0.9940119760  0.9860050891  0.9630573248  64.670658682  0.8174974660  2.2566514015  2700          0.1721112084 
0.9352704772  0.9768433949  0.9316656498  0.9388753056  0.9984008529  0.9700854701  1.0000000000  0.9910179641  0.9853689567  0.9694267516  71.856287425  0.8024295779  2.2566514015  3000          0.1708237457 
0.9349654132  0.9795436507  0.9310555217  0.9388753056  0.9984008529  0.9786324786  1.0000000000  0.9880239521  0.9863231552  0.9719745223  79.041916167  0.7473305663  2.2566514015  3300          0.1710815732 
0.9340479834  0.9765440318  0.9316656498  0.9364303178  0.9978678038  0.9658119658  1.0000000000  0.9880239521  0.9917302799  0.9757961783  86.227544910  0.5315505384  5.3973727226  3600          0.2097249850 
0.9346581115  0.9755713786  0.9328859060  0.9364303178  1.0000000000  0.9743589744  1.0000000000  0.9880239521  0.9901399491  0.9643312102  93.413173652  0.4414511222  5.3973727226  3900          0.2109590554 
0.9349631755  0.9778432679  0.9334960342  0.9364303178  0.9984008529  0.9743589744  1.0000000000  0.9910179641  0.9907760814  0.9681528662  100.59880239  0.4085836221  5.3973727226  4200          0.2086491036 
0.9343508098  0.9811131612  0.9347162904  0.9339853301  0.9978678038  0.9743589744  1.0000000000  0.9970059880  0.9904580153  0.9719745223  107.78443113  0.3844828594  5.3973727226  4500          0.2088277912 
0.9349609379  0.9795399127  0.9359365467  0.9339853301  0.9994669510  0.9700854701  1.0000000000  0.9940119760  0.9904580153  0.9745222930  114.97005988  0.3657255274  5.3973727226  4800          0.2074795922 
0.9355710660  0.9811131612  0.9371568029  0.9339853301  1.0000000000  0.9743589744  1.0000000000  0.9970059880  0.9869592875  0.9719745223  119.76047904  0.3655422448  5.3973727226  5000          0.2094074190 
