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: [0]
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/cc80ad3ae0528b04142ce57b9a8bd7cc
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1754839705
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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: 0.7419102898692578
	lambda2: 0.5215383105176172
	last_k_epoch: 0.23762453204831346
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.9748462276330736
	weight_decay: 1e-06
	worst_case_p: 0.3
using normal transform
using augment transform
using augment 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    
0.4942579503  0.3161563547  0.5044169611  0.4840989399  0.3327058824  0.3314500942  0.3438690023  0.3414634146  0.2880414661  0.2755555556  0.0000000000  3.1215548515  2.1691374779  0             1.5965507030 
0.9836572433  0.8025424747  0.9849823322  0.9823321555  0.7501176471  0.7514124294  0.8648134044  0.7865853659  0.9107737875  0.8696296296  8.4805653710  1.8103046060  2.4361162186  300           0.6400492803 
0.9871908122  0.8169838187  0.9849823322  0.9893992933  0.7858823529  0.7721280603  0.8941355674  0.8003048780  0.9318770826  0.8785185185  16.961130742  1.4095688526  2.4361162186  600           0.6434876362 
0.9858657239  0.8159707355  0.9858657244  0.9858657244  0.7929411765  0.7495291902  0.9265041889  0.8109756098  0.9459459459  0.8874074074  25.441696113  1.2828227933  2.4361162186  900           0.6437897452 
0.9854240278  0.8221582480  0.9885159011  0.9823321555  0.8103529412  0.7589453861  0.9360243717  0.8201219512  0.9577934098  0.8874074074  33.922261484  1.1789369478  2.4361162186  1200          0.6461025214 
0.9871908122  0.8131702976  0.9920494700  0.9823321555  0.8192941176  0.7514124294  0.9512566641  0.8140243902  0.9651980748  0.8740740741  42.402826855  1.0764487141  2.4361162186  1500          0.6450562684 
0.9889575967  0.8107625074  0.9920494700  0.9858657244  0.8400000000  0.7608286252  0.9600152323  0.8018292683  0.9718622732  0.8696296296  50.883392226  1.0088844260  2.4361162186  1800          0.6424403056 
0.9889575967  0.8234412876  0.9920494700  0.9858657244  0.8527058824  0.7702448211  0.9687738005  0.8185975610  0.9792669382  0.8814814815  59.363957597  0.9816919907  2.4361162186  2100          0.6382704910 
0.9885159006  0.8218412488  0.9911660777  0.9858657244  0.8687058824  0.7608286252  0.9760091394  0.8246951220  0.9825990374  0.8800000000  67.844522968  0.9548663859  2.4361162186  2400          0.6341883747 
0.9880742045  0.8164778066  0.9902826855  0.9858657244  0.8771764706  0.7570621469  0.9771515613  0.8079268293  0.9877823029  0.8844444444  76.325088339  0.9449189274  2.4361162186  2700          0.6426037049 
0.9885159006  0.8196256485  0.9911660777  0.9858657244  0.8945882353  0.7645951036  0.9794364052  0.8231707317  0.9877823029  0.8711111111  84.805653710  0.9363937285  2.4361162186  3000          0.6250162045 
0.9885159006  0.8232920064  0.9911660777  0.9858657244  0.9058823529  0.7758945386  0.9851485149  0.8125000000  0.9870418364  0.8814814815  93.286219081  0.9218999531  2.4361162186  3300          0.6361102454 
0.9885159006  0.8202299820  0.9911660777  0.9858657244  0.9120000000  0.7683615819  0.9840060929  0.8064024390  0.9918548686  0.8859259259  101.76678445  0.9183494443  2.4361162186  3600          0.6303673665 
0.9885159006  0.8200755079  0.9911660777  0.9858657244  0.9138823529  0.7721280603  0.9881949733  0.8140243902  0.9903739356  0.8740740741  110.24734982  0.8110285989  5.3990564346  3900          0.6196238367 
0.9885159006  0.8204988795  0.9911660777  0.9858657244  0.9200000000  0.7645951036  0.9904798172  0.8109756098  0.9940762680  0.8859259259  118.72791519  0.5451436196  5.3990564346  4200          0.6280549796 
0.9889575967  0.8222911082  0.9920494700  0.9858657244  0.9242352941  0.7683615819  0.9874333587  0.8155487805  0.9925953351  0.8829629630  127.20848056  0.5247143445  5.3990564346  4500          0.6213060228 
0.9885159006  0.8175707743  0.9911660777  0.9858657244  0.9289411765  0.7589453861  0.9900990099  0.8048780488  0.9925953351  0.8888888889  135.68904593  0.5145682196  5.3990564346  4800          0.6170438719 
0.9885159006  0.8238287423  0.9911660777  0.9858657244  0.9331764706  0.7758945386  0.9931454684  0.8170731707  0.9937060348  0.8785185185  141.34275618  0.5090065016  5.3990564346  5000          0.6274405265 
