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: 3
	output_dir: sweep/ablation3/outputs/44d240633b8c62c781142c4a0eed01c3
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1113450937
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	trial_seed: 2
	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: 0.5694511041907044
	lambda2: 0.6621108818243455
	last_k_epoch: 0.20248994529588413
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.502579147595572
	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    
0.0854510056  0.1739934024  0.1342281879  0.1320293399  0.1583155650  0.1474358974  0.2350299401  0.2425149701  0.0919211196  0.0789808917  0.0000000000  8.1477203369  1.7945718765  0             1.5331215858 
0.7646425905  0.9564670626  0.9719341062  0.9437652812  0.9712153518  0.9316239316  0.9977544910  0.9940119760  0.7611323155  0.7681528662  7.1856287425  2.7437916746  2.0946040154  300           0.1417130748 
0.8021978975  0.9711075411  0.9908480781  0.9633251834  0.9941364606  0.9529914530  0.9992514970  0.9970059880  0.7993002545  0.8050955414  14.371257485  0.9337700711  2.0946040154  600           0.1617804241 
0.8023577410  0.9734273013  0.9969493594  0.9608801956  0.9952025586  0.9594017094  1.0000000000  1.0000000000  0.7983460560  0.8063694268  21.556886227  0.8041920035  2.0946040154  900           0.1604806757 
0.7894647165  0.9784355387  0.9957291031  0.9682151589  0.9946695096  0.9700854701  1.0000000000  0.9970059880  0.7903944020  0.7885350318  28.742514970  0.7319590690  2.0946040154  1200          0.1624467166 
0.7905811895  0.9762987865  0.9969493594  0.9682151589  0.9984008529  0.9636752137  1.0000000000  0.9970059880  0.7875318066  0.7936305732  35.928143712  0.6763646564  2.0946040154  1500          0.1626881957 
0.7910566681  0.9799627853  0.9993898719  0.9706601467  0.9989339019  0.9722222222  0.9992514970  0.9970059880  0.7910305344  0.7910828025  43.113772455  0.6842779222  2.0946040154  1800          0.1619793375 
0.7942365193  0.9782300483  0.9981696156  0.9633251834  0.9994669510  0.9743589744  1.0000000000  0.9970059880  0.7986641221  0.7898089172  50.299401197  0.6353749421  2.0946040154  2100          0.1622432605 
0.7974196119  0.9757047976  0.9993898719  0.9608801956  0.9984008529  0.9722222222  1.0000000000  0.9940119760  0.8012086514  0.7936305732  57.485029940  0.6314573517  2.0946040154  2400          0.1629212968 
0.7953513715  0.9826062977  1.0000000000  0.9657701711  0.9989339019  0.9850427350  1.0000000000  0.9970059880  0.7983460560  0.7923566879  64.670658682  0.6089995438  2.0946040154  2700          0.1629890577 
0.7985336538  0.9743830414  1.0000000000  0.9633251834  0.9994669510  0.9658119658  1.0000000000  0.9940119760  0.8021628499  0.7949044586  71.856287425  0.6062694458  2.0946040154  3000          0.1621896950 
0.8034669207  0.9753810454  1.0000000000  0.9633251834  1.0000000000  0.9658119658  1.0000000000  0.9970059880  0.8069338422  0.8000000000  79.041916167  0.5867847726  2.0946040154  3300          0.1631316328 
0.8068090465  0.9817913018  1.0000000000  0.9633251834  1.0000000000  0.9850427350  1.0000000000  0.9970059880  0.8097964377  0.8038216561  86.227544910  0.6117526631  2.0946040154  3600          0.1628717566 
0.8082427752  0.9755217896  1.0000000000  0.9633251834  0.9994669510  0.9722222222  1.0000000000  0.9910179641  0.8088422392  0.8076433121  93.413173652  0.5810049342  2.0946040154  3900          0.1610574595 
0.8104708591  0.9780470402  1.0000000000  0.9657701711  0.9984008529  0.9743589744  1.0000000000  0.9940119760  0.8107506361  0.8101910828  100.59880239  0.5016987668  5.3997893333  4200          0.1931463949 
0.8134949186  0.9797572949  0.9993898719  0.9657701711  0.9994669510  0.9764957265  1.0000000000  0.9970059880  0.8129770992  0.8140127389  107.78443113  0.3872843544  5.3997893333  4500          0.2078334554 
0.8134957290  0.9835240389  1.0000000000  0.9706601467  0.9989339019  0.9829059829  1.0000000000  0.9970059880  0.8117048346  0.8152866242  114.97005988  0.3497591683  5.3997893333  4800          0.2057199438 
0.8160426893  0.9826287801  1.0000000000  0.9731051345  1.0000000000  0.9807692308  0.9992514970  0.9940119760  0.8129770992  0.8191082803  119.76047904  0.3254334310  5.3997893333  5000          0.2080320728 
