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: VLCS
	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/237204956f5c0366e81344bd70d89146
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 2056062500
	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    
0.2592145569  0.2262592481  0.1810954064  0.1696113074  0.2225882353  0.2241054614  0.2867479056  0.2850609756  0.2413920770  0.2770370370  0.0000000000  3.2902240753  1.7945408821  0             1.5358014107 
0.8017047180  0.8471707979  0.9991166078  0.9929328622  0.7877647059  0.7589453861  0.8724295506  0.7896341463  0.7945205479  0.8088888889  8.4805653710  1.7899155740  2.0945272446  300           0.6446890418 
0.8126274215  0.8683036505  1.0000000000  0.9929328622  0.8240000000  0.7796610169  0.9242193450  0.8323170732  0.8119215106  0.8133333333  16.961130742  1.3560017196  2.0945272446  600           0.6596558181 
0.8172564341  0.8700499235  1.0000000000  0.9964664311  0.8432941176  0.7966101695  0.9489718203  0.8170731707  0.8152536098  0.8192592593  25.441696113  1.2334328745  2.0945272446  900           0.6462400301 
0.8211449802  0.8694395270  1.0000000000  0.9929328622  0.8663529412  0.7815442561  0.9649657273  0.8338414634  0.8171047760  0.8251851852  33.922261484  1.1339165229  2.0945272446  1200          0.6605050270 
0.8242925113  0.8672517337  1.0000000000  1.0000000000  0.8856470588  0.7740112994  0.9767707540  0.8277439024  0.8204368752  0.8281481481  42.402826855  0.9899118022  2.0945272446  1500          0.6511300826 
0.8168862009  0.8706593631  1.0000000000  1.0000000000  0.9115294118  0.7796610169  0.9832444783  0.8323170732  0.8145131433  0.8192592593  50.883392226  0.9174998637  2.0945272446  1800          0.6521425088 
0.8124425792  0.8687464591  1.0000000000  1.0000000000  0.9209411765  0.7815442561  0.9893373953  0.8246951220  0.8100703443  0.8148148148  59.363957597  0.8901454854  2.0945272446  2100          0.6455411140 
0.8126274215  0.8711674932  1.0000000000  1.0000000000  0.9374117647  0.7796610169  0.9927646611  0.8338414634  0.8119215106  0.8133333333  67.844522968  0.8649666272  2.0945272446  2400          0.6467833257 
0.8135530047  0.8711674932  1.0000000000  1.0000000000  0.9496470588  0.7796610169  0.9942878903  0.8338414634  0.8137726768  0.8133333333  76.325088339  0.8599069182  2.0945272446  2700          0.6529274249 
0.8137383955  0.8748143552  1.0000000000  1.0000000000  0.9552941176  0.7890772128  0.9961919269  0.8353658537  0.8126619770  0.8148148148  84.805653710  0.8456569143  2.0945272446  3000          0.6461333243 
0.8150344861  0.8721540885  1.0000000000  1.0000000000  0.9637647059  0.7871939736  0.9969535415  0.8292682927  0.8137726768  0.8162962963  93.286219081  0.8489533454  2.0945272446  3300          0.6479878394 
0.8167013585  0.8727398550  1.0000000000  0.9964664311  0.9750588235  0.7909604520  0.9973343488  0.8307926829  0.8126619770  0.8207407407  101.76678445  0.8574415972  2.0945272446  3600          0.6497404106 
0.8144791363  0.8716459584  1.0000000000  1.0000000000  0.9778823529  0.7871939736  0.9992383854  0.8277439024  0.8126619770  0.8162962963  110.24734982  0.8832311781  2.0945272446  3900          0.6461600192 
0.8135530047  0.8778334708  1.0000000000  1.0000000000  0.9769411765  0.7966101695  0.9980959634  0.8368902439  0.8137726768  0.8133333333  118.72791519  0.5572659402  5.3997030258  4200          0.6418328691 
0.8150342119  0.8696011231  1.0000000000  0.9964664311  0.9835294118  0.7815442561  0.9992383854  0.8307926829  0.8152536098  0.8148148148  127.20848056  0.4014799400  5.3997030258  4500          0.6418729838 
0.8148490953  0.8716039786  1.0000000000  0.9964664311  0.9797647059  0.7890772128  0.9992383854  0.8292682927  0.8148833765  0.8148148148  135.68904593  0.3831737721  5.3997030258  4800          0.6494380665 
0.8142937454  0.8725722671  1.0000000000  1.0000000000  0.9840000000  0.7777777778  0.9984767708  0.8399390244  0.8137726768  0.8148148148  141.34275618  0.3747843134  5.3997030258  5000          0.6386212552 
