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: [1]
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/2ff4a814f9957f6d386dbf37e1bc5560
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 135225809
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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 normal 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    
0.1632952453  0.1457037958  0.1891397193  0.1540342298  0.1556503198  0.1709401709  0.1384730539  0.1556886228  0.1186386768  0.1273885350  0.0000000000  6.4094247818  1.7945718765  0             1.4948372841 
0.8044097275  0.9517267581  0.9755948749  0.9388753056  0.8224946695  0.7863247863  0.9970059880  0.9940119760  0.9513358779  0.9222929936  7.1856287425  2.1809103984  2.0946040154  300           0.1463447722 
0.8463064709  0.9646504132  0.9938987187  0.9559902200  0.8571428571  0.8354700855  0.9992514970  0.9940119760  0.9742366412  0.9439490446  14.371257485  0.9925762588  2.0946040154  600           0.1629981263 
0.8591224277  0.9712731636  0.9938987187  0.9682151589  0.8614072495  0.8568376068  0.9992514970  0.9940119760  0.9805979644  0.9515923567  21.556886227  0.8986054393  2.0946040154  900           0.1631455866 
0.8607215748  0.9655925434  0.9981696156  0.9584352078  0.8646055437  0.8568376068  1.0000000000  0.9880239521  0.9796437659  0.9503184713  28.742514970  0.8089698189  2.0946040154  1200          0.1641197252 
0.8615234264  0.9692870652  0.9987797437  0.9584352078  0.8640724947  0.8589743590  1.0000000000  0.9940119760  0.9863231552  0.9554140127  35.928143712  0.8034194438  2.0946040154  1500          0.1635822797 
0.8671272753  0.9699190531  0.9987797437  0.9633251834  0.8688699360  0.8653846154  1.0000000000  0.9910179641  0.9872773537  0.9554140127  43.113772455  0.7671050781  2.0946040154  1800          0.1642747561 
0.8687309784  0.9718005749  1.0000000000  0.9608801956  0.8678038380  0.8696581197  0.9992514970  0.9940119760  0.9882315522  0.9605095541  50.299401197  0.7399633766  2.0946040154  2100          0.1639602971 
0.8695328299  0.9770006928  0.9981696156  0.9731051345  0.8672707889  0.8717948718  1.0000000000  0.9910179641  0.9901399491  0.9668789809  57.485029940  0.7501750469  2.0946040154  2400          0.1662317761 
0.8673983558  0.9735450529  0.9987797437  0.9682151589  0.8651385928  0.8696581197  1.0000000000  0.9970059880  0.9904580153  0.9554140127  64.670658682  0.7190219903  2.0946040154  2700          0.1686165420 
0.8708677305  0.9722594644  1.0000000000  0.9584352078  0.8678038380  0.8739316239  0.9992514970  0.9940119760  0.9914122137  0.9643312102  71.856287425  0.7080709621  2.0946040154  3000          0.1665975277 
0.8708700085  0.9757953294  0.9993898719  0.9682151589  0.8656716418  0.8760683761  1.0000000000  0.9910179641  0.9933206107  0.9681528662  79.041916167  0.7754546058  2.0946040154  3300          0.1664886030 
0.8708677305  0.9725254361  1.0000000000  0.9682151589  0.8678038380  0.8739316239  1.0000000000  0.9850299401  0.9926844784  0.9643312102  86.227544910  0.5064078399  5.4005656242  3600          0.1900150013 
0.8692663054  0.9741067253  0.9993898719  0.9584352078  0.8667377399  0.8717948718  1.0000000000  0.9970059880  0.9926844784  0.9668789809  93.413173652  0.2919305138  5.4005656242  3900          0.2122751419 
0.8692685834  0.9773324480  1.0000000000  0.9706601467  0.8646055437  0.8739316239  1.0000000000  0.9970059880  0.9917302799  0.9643312102  100.59880239  0.2787579080  5.4005656242  4200          0.2103974756 
0.8687332564  0.9753364400  1.0000000000  0.9706601467  0.8656716418  0.8717948718  1.0000000000  0.9910179641  0.9945928753  0.9643312102  107.78443113  0.2668745014  5.4005656242  4500          0.2093273123 
0.8695351079  0.9777228155  0.9993898719  0.9731051345  0.8651385928  0.8739316239  1.0000000000  0.9970059880  0.9920483461  0.9630573248  114.97005988  0.2567282546  5.4005656242  4800          0.2071386854 
0.8700681569  0.9755879700  1.0000000000  0.9633251834  0.8662046908  0.8739316239  0.9992514970  0.9940119760  0.9939567430  0.9694267516  119.76047904  0.2534212305  5.4005656242  5000          0.2061097383 
