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/623fdd0418867600742f1078791ea6d5
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1727539050
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	trial_seed: 0
	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: 0.7010166027828918
	lambda2: 0.6269010951324223
	last_k_epoch: 0.38851977780027735
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.131347198605345
	weight_decay: 1e-06
	worst_case_p: 0.3
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    
0.0612625808  0.0887086817  0.0829774253  0.0904645477  0.1332622601  0.1517094017  0.0501497006  0.0239520958  0.0677480916  0.0547770701  0.0000000000  8.3443031311  2.1691875458  0             2.3396730423 
0.7176978489  0.9658515495  0.9786455156  0.9535452323  0.9813432836  0.9529914530  0.9962574850  0.9910179641  0.7143765903  0.7210191083  7.1856287425  2.0742965828  2.4361939430  300           0.1521074263 
0.7681429390  0.9745885318  0.9896278218  0.9682151589  0.9925373134  0.9615384615  0.9992514970  0.9940119760  0.7655852417  0.7707006369  14.371257485  0.7964251223  2.4361939430  600           0.1698018869 
0.7909033075  0.9772967905  0.9932885906  0.9682151589  0.9973347548  0.9636752137  0.9985029940  1.0000000000  0.7818066158  0.8000000000  21.556886227  0.6928256894  2.4361939430  900           0.1686544450 
0.7845387429  0.9765197936  0.9963392312  0.9633251834  0.9962686567  0.9722222222  1.0000000000  0.9940119760  0.7741730280  0.7949044586  28.742514970  0.6407551064  2.4361939430  1200          0.1770761975 
0.7964767585  0.9762763042  0.9945088469  0.9608801956  0.9984008529  0.9679487179  1.0000000000  1.0000000000  0.7814885496  0.8114649682  35.928143712  0.6174766078  2.4361939430  1500          0.1770816755 
0.8004542062  0.9768055468  0.9987797437  0.9633251834  0.9973347548  0.9700854701  1.0000000000  0.9970059880  0.7868956743  0.8140127389  43.113772455  0.5900600563  2.4361939430  1800          0.1746431152 
0.8010919592  0.9751980373  0.9969493594  0.9657701711  0.9984008529  0.9658119658  0.9992514970  0.9940119760  0.7856234097  0.8165605096  50.299401197  0.5778323154  2.4361939430  2100          0.1756114936 
0.8002943627  0.9749122841  0.9987797437  0.9657701711  0.9989339019  0.9679487179  1.0000000000  0.9910179641  0.7878498728  0.8127388535  57.485029940  0.5757698739  2.4361939430  2400          0.1767004418 
0.7980654686  0.9808805265  1.0000000000  0.9755501222  0.9989339019  0.9700854701  1.0000000000  0.9970059880  0.7872137405  0.8089171975  64.670658682  0.5533715611  2.4361939430  2700          0.1735154780 
0.7972686824  0.9791477894  0.9981696156  0.9682151589  0.9978678038  0.9722222222  1.0000000000  0.9970059880  0.7881679389  0.8063694268  71.856287425  0.5344255793  2.4361939430  3000          0.1746003191 
0.7926534817  0.9758075428  0.9981696156  0.9633251834  0.9978678038  0.9700854701  1.0000000000  0.9940119760  0.7840330789  0.8012738854  79.041916167  0.3616683816  5.3991427422  3300          0.2031787022 
0.7929715479  0.9806750360  0.9993898719  0.9706601467  0.9994669510  0.9743589744  1.0000000000  0.9970059880  0.7846692112  0.8012738854  86.227544910  0.2863759704  5.3991427422  3600          0.2110649538 
0.7923337948  0.9782300483  1.0000000000  0.9633251834  1.0000000000  0.9743589744  1.0000000000  0.9970059880  0.7859414758  0.7987261146  93.413173652  0.2699131296  5.3991427422  3900          0.2116871214 
0.7926526714  0.9792505346  0.9993898719  0.9706601467  0.9994669510  0.9700854701  1.0000000000  0.9970059880  0.7853053435  0.8000000000  100.59880239  0.2559364611  5.3991427422  4200          0.2089719137 
0.7956767309  0.9715495552  0.9993898719  0.9535452323  0.9978678038  0.9700854701  1.0000000000  0.9910179641  0.7875318066  0.8038216561  107.78443113  0.2492846045  5.3991427422  4500          0.2083270971 
0.7947217221  0.9793757622  0.9969493594  0.9804400978  0.9994669510  0.9636752137  1.0000000000  0.9940119760  0.7868956743  0.8025477707  114.97005988  0.2419379995  5.3991427422  4800          0.2082254299 
0.7942430021  0.9797797773  0.9993898719  0.9731051345  0.9989339019  0.9722222222  1.0000000000  0.9940119760  0.7884860051  0.8000000000  119.76047904  0.2388733870  5.3991427422  5000          0.2093431890 
