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: 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/aa7974f1536c9287e375ef87ac19e7be
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1112003737
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	trial_seed: 1
	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: 0.6171767606394463
	lambda2: 0.5293911814442921
	last_k_epoch: 0.3102645027326114
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.022572617872769
	weight_decay: 0.0001
	worst_case_p: 0.2
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    
0.1903267369  0.2106907431  0.1665649786  0.1955990220  0.2169509595  0.2628205128  0.1549401198  0.1736526946  0.1870229008  0.1936305732  0.0000000000  7.6479673386  1.7945718765  0             1.4951040745 
0.7463400103  0.9628773190  0.9768151312  0.9437652812  0.9808102345  0.9508547009  0.9977544910  0.9940119760  0.7461832061  0.7464968153  7.1856287425  2.2143332295  2.0946040154  300           0.1506567915 
0.7851659613  0.9668495534  0.9938987187  0.9535452323  0.9941364606  0.9529914530  1.0000000000  0.9940119760  0.7894402036  0.7808917197  14.371257485  0.8380479552  2.0946040154  600           0.1648590819 
0.7982147773  0.9707190426  0.9969493594  0.9608801956  0.9962686567  0.9572649573  1.0000000000  0.9940119760  0.8027989822  0.7936305732  21.556886227  0.7129378279  2.0946040154  900           0.1637656792 
0.7967818589  0.9754613083  0.9975594875  0.9584352078  0.9978678038  0.9679487179  1.0000000000  1.0000000000  0.8024809160  0.7910828025  28.742514970  0.6790147637  2.0946040154  1200          0.1646018823 
0.8020348126  0.9740748058  0.9993898719  0.9559902200  0.9962686567  0.9722222222  1.0000000000  0.9940119760  0.8053435115  0.7987261146  35.928143712  0.6511487003  2.0946040154  1500          0.1643347565 
0.8103118260  0.9714692923  0.9975594875  0.9584352078  0.9984008529  0.9679487179  1.0000000000  0.9880239521  0.8104325700  0.8101910828  43.113772455  0.6400962009  2.0946040154  1800          0.1644183222 
0.8117431237  0.9798600401  0.9987797437  0.9682151589  0.9978678038  0.9743589744  0.9992514970  0.9970059880  0.8132951654  0.8101910828  50.299401197  0.6204989045  2.0946040154  2100          0.1631493934 
0.8142900840  0.9804920280  0.9987797437  0.9731051345  0.9989339019  0.9743589744  1.0000000000  0.9940119760  0.8145674300  0.8140127389  57.485029940  0.6011799655  2.0946040154  2400          0.1645157997 
0.8176322098  0.9794715416  0.9993898719  0.9657701711  0.9984008529  0.9786324786  1.0000000000  0.9940119760  0.8174300254  0.8178343949  64.670658682  0.6138575824  2.0946040154  2700          0.1649832702 
0.8184265648  0.9773347895  0.9993898719  0.9657701711  0.9989339019  0.9722222222  1.0000000000  0.9940119760  0.8202926209  0.8165605096  71.856287425  0.5898108441  2.0946040154  3000          0.1633623783 
0.8173133332  0.9792660512  0.9993898719  0.9608801956  0.9994669510  0.9829059829  1.0000000000  0.9940119760  0.8180661578  0.8165605096  79.041916167  0.5875524553  2.0946040154  3300          0.1649540663 
0.8201799805  0.9767632829  0.9993898719  0.9657701711  0.9989339019  0.9764957265  1.0000000000  0.9880239521  0.8174300254  0.8229299363  86.227544910  0.4406540787  5.4005656242  3600          0.1865642460 
0.8209759562  0.9829525323  0.9993898719  0.9706601467  1.0000000000  0.9871794872  0.9992514970  0.9910179641  0.8177480916  0.8242038217  93.413173652  0.2679150158  5.4005656242  3900          0.2091341050 
0.8228851635  0.9820192746  0.9987797437  0.9755501222  1.0000000000  0.9764957265  1.0000000000  0.9940119760  0.8202926209  0.8254777070  100.59880239  0.2445998948  5.4005656242  4200          0.2076826811 
0.8222482208  0.9801035295  0.9987797437  0.9706601467  0.9984008529  0.9786324786  1.0000000000  0.9910179641  0.8202926209  0.8242038217  107.78443113  0.2337892377  5.4005656242  4500          0.2077147810 
0.8225662870  0.9753162991  0.9993898719  0.9584352078  0.9989339019  0.9764957265  1.0000000000  0.9910179641  0.8209287532  0.8242038217  114.97005988  0.2256324747  5.4005656242  4800          0.2083023198 
0.8241574282  0.9796545497  1.0000000000  0.9633251834  0.9994669510  0.9786324786  1.0000000000  0.9970059880  0.8228371501  0.8254777070  119.76047904  0.2192752775  5.4005656242  5000          0.2080853307 
