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: [2]
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: 2
	output_dir: sweep/ablation3/outputs/e15bc5729fd963c0f41bdef45813fadd
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 682030220
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	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 augment transform
using normal 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    
0.2794278137  0.1765812591  0.2058303887  0.1660777385  0.2004705882  0.1977401130  0.2814166032  0.2774390244  0.1806738245  0.1659259259  0.0000000000  4.0401163101  2.1691374779  0             1.4511675835 
0.7918156610  0.8596009778  1.0000000000  0.9893992933  0.7858823529  0.7419962335  0.7757044935  0.8079268293  0.9263235839  0.8474074074  8.4805653710  1.5661288617  2.4361162186  300           0.6178538775 
0.7990492584  0.8723689105  1.0000000000  0.9964664311  0.8301176471  0.7495291902  0.7947448591  0.8033536585  0.9633469086  0.8711111111  16.961130742  1.0953809025  2.4361162186  600           0.6240473342 
0.7931438426  0.8759238331  1.0000000000  1.0000000000  0.8635294118  0.7551789077  0.7905559787  0.7957317073  0.9733432062  0.8725925926  25.441696113  0.9269905033  2.4361162186  900           0.6257233381 
0.7918104365  0.8744637054  1.0000000000  0.9929328622  0.8941176471  0.7608286252  0.7894135567  0.7942073171  0.9833395039  0.8696296296  33.922261484  0.8271210315  2.4361162186  1200          0.6195999193 
0.7912392255  0.8714231060  1.0000000000  0.9964664311  0.9138823529  0.7570621469  0.7882711348  0.7942073171  0.9877823029  0.8607407407  42.402826855  0.7643794600  2.4361162186  1500          0.6180297263 
0.7900962231  0.8803180579  1.0000000000  1.0000000000  0.9350588235  0.7683615819  0.7875095202  0.7926829268  0.9940762680  0.8725925926  50.883392226  0.7363421430  2.4361162186  1800          0.6265750003 
0.7883820097  0.8823710030  1.0000000000  0.9964664311  0.9515294118  0.7721280603  0.7856054836  0.7911585366  0.9933358016  0.8785185185  59.363957597  0.7163180361  2.4361162186  2100          0.6237189865 
0.7830489659  0.8835070095  1.0000000000  1.0000000000  0.9576470588  0.7645951036  0.7795125666  0.7865853659  0.9955572010  0.8859259259  67.844522968  0.7564336129  2.4361162186  2400          0.6238569657 
0.7836207573  0.8767631352  1.0000000000  0.9964664311  0.9755294118  0.7627118644  0.7791317593  0.7881097561  0.9951869678  0.8711111111  76.325088339  0.7026558657  2.4361162186  2700          0.6296768498 
0.7824777549  0.8803394116  1.0000000000  0.9929328622  0.9783529412  0.7740112994  0.7783701447  0.7865853659  0.9962976675  0.8740740741  84.805653710  0.6942018384  2.4361162186  3000          0.6297621616 
0.7809533646  0.8780749108  1.0000000000  1.0000000000  0.9816470588  0.7645951036  0.7783701447  0.7835365854  0.9962976675  0.8696296296  93.286219081  0.4768898707  5.3990564346  3300          0.6184010514 
0.7798103622  0.8771648929  1.0000000000  0.9964664311  0.9825882353  0.7683615819  0.7776085301  0.7820121951  0.9981488338  0.8666666667  101.76678445  0.3524510081  5.3990564346  3600          0.6393546669 
0.7817161403  0.8798660805  1.0000000000  1.0000000000  0.9849411765  0.7758945386  0.7768469155  0.7865853659  0.9974083673  0.8637037037  110.24734982  0.3355924477  5.3990564346  3900          0.6285951519 
0.7788583439  0.8773550949  1.0000000000  1.0000000000  0.9863529412  0.7683615819  0.7757044935  0.7820121951  0.9985190670  0.8637037037  118.72791519  0.3233689999  5.3990564346  4200          0.6282135487 
0.7796205391  0.8829211129  1.0000000000  1.0000000000  0.9868235294  0.7702448211  0.7757044935  0.7835365854  0.9988893003  0.8785185185  127.20848056  0.3187048145  5.3990564346  4500          0.6319628310 
0.7788589244  0.8742521497  1.0000000000  0.9964664311  0.9924705882  0.7551789077  0.7741812643  0.7835365854  0.9985190670  0.8711111111  135.68904593  0.3179781609  5.3990564346  4800          0.6306462097 
0.7773351147  0.8816656201  1.0000000000  1.0000000000  0.9901176471  0.7664783427  0.7726580350  0.7820121951  0.9981488338  0.8785185185  141.34275618  0.3109804689  5.3990564346  5000          0.6061967719 
