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: 1
	output_dir: sweep/ablation3/outputs/39525bdcb4223635350620b983f2a729
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1568730028
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	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: 0.6109302038716249
	lambda2: 0.5117744391412766
	last_k_epoch: 0.31317984427858747
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.002688876693512
	weight_decay: 1e-06
	worst_case_p: 0.25
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    
0.2769554686  0.2049141968  0.2632508834  0.2932862191  0.1312941176  0.1318267420  0.2688499619  0.2850609756  0.1769714920  0.1896296296  0.0000000000  3.1447935104  2.0073552132  0             1.6320204735 
0.7519934330  0.8856018044  1.0000000000  0.9964664311  0.7952941176  0.7758945386  0.7692307692  0.7347560976  0.9166975194  0.8844444444  8.4805653710  1.6957960494  2.2565736771  300           0.6276632086 
0.7916136474  0.8903703701  1.0000000000  1.0000000000  0.8174117647  0.7777777778  0.8057882711  0.7774390244  0.9533506109  0.8933333333  16.961130742  1.2350890712  2.2565736771  600           0.6411993694 
0.7916142279  0.8936932410  1.0000000000  1.0000000000  0.8517647059  0.7758945386  0.8042650419  0.7789634146  0.9674194743  0.9051851852  25.441696113  1.0709431960  2.2565736771  900           0.6338498084 
0.7849477779  0.8936011715  1.0000000000  1.0000000000  0.8842352941  0.7815442561  0.7970297030  0.7728658537  0.9800074047  0.8992592593  33.922261484  0.9383203290  2.2565736771  1200          0.6414348880 
0.7801865255  0.8917955688  1.0000000000  0.9964664311  0.9040000000  0.7796610169  0.7905559787  0.7698170732  0.9833395039  0.8992592593  42.402826855  0.9028092110  2.2565736771  1500          0.6359197561 
0.7761857268  0.8901383183  1.0000000000  0.9964664311  0.9209411765  0.7702448211  0.7886519421  0.7637195122  0.9911144021  0.9037037037  50.883392226  0.8494220320  2.2565736771  1800          0.6537394476 
0.7756150963  0.8871335056  1.0000000000  0.9964664311  0.9392941176  0.7627118644  0.7859862909  0.7652439024  0.9896334691  0.9022222222  59.363957597  0.8181609261  2.2565736771  2100          0.6416217192 
0.7748534817  0.8891148773  1.0000000000  1.0000000000  0.9444705882  0.7740112994  0.7844630617  0.7652439024  0.9922251018  0.8933333333  67.844522968  0.8060332117  2.2565736771  2400          0.6412845143 
0.7752342890  0.8869135800  1.0000000000  1.0000000000  0.9642352941  0.7777777778  0.7852246763  0.7652439024  0.9925953351  0.8829629630  76.325088339  0.8125245780  2.2565736771  2700          0.6453765432 
0.7729477036  0.8816656201  1.0000000000  1.0000000000  0.9647058824  0.7664783427  0.7852246763  0.7606707317  0.9955572010  0.8785185185  84.805653710  0.7900406380  2.2565736771  3000          0.6444826190 
0.7737098987  0.8840282535  1.0000000000  0.9964664311  0.9708235294  0.7815442561  0.7852246763  0.7621951220  0.9959274343  0.8740740741  93.286219081  0.7908695183  2.2565736771  3300          0.6500251317 
0.7716142975  0.8835070095  1.0000000000  1.0000000000  0.9783529412  0.7645951036  0.7840822544  0.7591463415  0.9966679008  0.8859259259  101.76678445  0.5798490872  5.3972864151  3600          0.6399591486 
0.7672315305  0.8869493667  1.0000000000  0.9964664311  0.9811764706  0.7740112994  0.7844630617  0.7500000000  0.9981488338  0.8903703704  110.24734982  0.3688430263  5.3972864151  3900          0.6586681859 
0.7632307317  0.8858277931  1.0000000000  0.9964664311  0.9792941176  0.7721280603  0.7825590251  0.7439024390  0.9974083673  0.8888888889  118.72791519  0.3565645821  5.3972864151  4200          0.6496640778 
0.7626589402  0.8889809581  1.0000000000  1.0000000000  0.9849411765  0.7721280603  0.7829398324  0.7423780488  0.9974083673  0.8948148148  127.20848056  0.3423896052  5.3972864151  4500          0.6519057035 
0.7645641378  0.8927474364  1.0000000000  1.0000000000  0.9830588235  0.7834274953  0.7837014471  0.7454268293  0.9985190670  0.8948148148  135.68904593  0.3347783117  5.3972864151  4800          0.6482648102 
0.7651359293  0.8871395687  1.0000000000  1.0000000000  0.9840000000  0.7740112994  0.7833206398  0.7469512195  0.9966679008  0.8874074074  141.34275618  0.3299263436  5.3972864151  5000          0.6506200910 
