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: 2
	output_dir: sweep/ablation3/outputs/da142e489de14bb5c4f7328509001b00
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1015540564
	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: 0.5439617198173775
	lambda2: 0.5509403872292429
	last_k_epoch: 0.38252238504986713
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.920147743151585
	weight_decay: 1e-06
	worst_case_p: 0.3
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    
0.1707715998  0.2322319961  0.1348383160  0.1295843521  0.1577825160  0.1837606838  0.2799401198  0.3263473054  0.2452290076  0.2407643312  0.0000000000  8.1104249954  2.1691875458  0             1.5514729023 
0.8116241135  0.9582106710  0.9841366687  0.9413202934  0.8198294243  0.8034188034  0.9985029940  0.9970059880  0.9611959288  0.9363057325  7.1856287425  2.0233866974  2.4373230934  300           0.1521977170 
0.8521905122  0.9740968156  0.9951189750  0.9682151589  0.8496801706  0.8547008547  1.0000000000  0.9910179641  0.9815521628  0.9630573248  14.371257485  0.8727225107  2.4373230934  600           0.1730404258 
0.8537919373  0.9720178440  0.9969493594  0.9559902200  0.8507462687  0.8568376068  0.9992514970  0.9970059880  0.9863231552  0.9630573248  21.556886227  0.7700530888  2.4373230934  900           0.1726025899 
0.8559286895  0.9756339342  1.0000000000  0.9706601467  0.8507462687  0.8611111111  1.0000000000  0.9970059880  0.9910941476  0.9592356688  28.742514970  0.7376106559  2.4373230934  1200          0.1727670479 
0.8596623107  0.9725109944  0.9987797437  0.9511002445  0.8560767591  0.8632478632  1.0000000000  0.9970059880  0.9901399491  0.9694267516  35.928143712  0.6757732849  2.4373230934  1500          0.1733523345 
0.8569879536  0.9740382033  0.9981696156  0.9633251834  0.8592750533  0.8547008547  1.0000000000  0.9970059880  0.9923664122  0.9617834395  43.113772455  0.6412498916  2.4373230934  1800          0.1725619713 
0.8553819725  0.9744285708  1.0000000000  0.9657701711  0.8624733475  0.8482905983  1.0000000000  0.9970059880  0.9914122137  0.9605095541  50.299401197  0.6322905663  2.4373230934  2100          0.1731057803 
0.8593889522  0.9767248115  1.0000000000  0.9731051345  0.8619402985  0.8568376068  1.0000000000  0.9940119760  0.9939567430  0.9630573248  57.485029940  0.6023878490  2.4373230934  2400          0.1785418502 
0.8591201497  0.9757024561  0.9987797437  0.9657701711  0.8635394456  0.8547008547  1.0000000000  0.9970059880  0.9939567430  0.9643312102  64.670658682  0.6012031024  2.4373230934  2700          0.1763138421 
0.8607192969  0.9756681952  0.9993898719  0.9682151589  0.8667377399  0.8547008547  1.0000000000  0.9970059880  0.9936386768  0.9617834395  71.856287425  0.5899650362  2.4373230934  3000          0.1801366369 
0.8625872465  0.9759098155  1.0000000000  0.9706601467  0.8683368870  0.8568376068  1.0000000000  0.9940119760  0.9968193384  0.9630573248  79.041916167  0.4542819077  5.3973193169  3300          0.2045490289 
0.8623184440  0.9734648278  0.9993898719  0.9633251834  0.8699360341  0.8547008547  1.0000000000  0.9940119760  0.9958651399  0.9630573248  86.227544910  0.3548146066  5.3973193169  3600          0.2147748661 
0.8599174453  0.9733160807  1.0000000000  0.9633251834  0.8672707889  0.8525641026  0.9992514970  0.9910179641  0.9955470738  0.9656050955  93.413173652  0.3263122162  5.3973193169  3900          0.2147090809 
0.8585825447  0.9760125985  1.0000000000  0.9633251834  0.8667377399  0.8504273504  1.0000000000  0.9940119760  0.9945928753  0.9707006369  100.59880239  0.3058460550  5.3973193169  4200          0.2159037304 
0.8607192969  0.9729815870  0.9993898719  0.9584352078  0.8667377399  0.8547008547  1.0000000000  1.0000000000  0.9961832061  0.9605095541  107.78443113  0.2960664477  5.3973193169  4500          0.2159225885 
0.8620564754  0.9752435667  1.0000000000  0.9682151589  0.8651385928  0.8589743590  1.0000000000  0.9970059880  0.9968193384  0.9605095541  114.97005988  0.2830942885  5.3973193169  4800          0.2169459462 
0.8609880994  0.9784233253  1.0000000000  0.9731051345  0.8651385928  0.8568376068  1.0000000000  0.9940119760  0.9965012723  0.9681528662  119.76047904  0.2843969348  5.3973193169  5000          0.2186587608 
