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: 1
	output_dir: sweep/ablation3/outputs/41608523de2a65e97aecd25d09d2ea02
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1400967867
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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: 0.7819049321936025
	lambda2: 0.9075316444347157
	last_k_epoch: 0.25491468830584113
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.907263233121133
	weight_decay: 1e-06
	worst_case_p: 0.25
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    
0.3736749115  0.2602806868  0.3727915194  0.3745583039  0.2527058824  0.2617702448  0.2524752475  0.2301829268  0.3013698630  0.2888888889  0.0000000000  3.9131917953  2.0073552132  0             1.6652476788 
0.9911660772  0.8001888213  0.9893992933  0.9929328622  0.7581176471  0.7438794727  0.8328255903  0.8033536585  0.9067012218  0.8533333333  8.4805653710  1.9610643502  2.2565736771  300           0.6498657258 
0.9920494695  0.8212665801  0.9911660777  0.9929328622  0.7849411765  0.7495291902  0.8941355674  0.8490853659  0.9274342836  0.8651851852  16.961130742  1.5436370258  2.2565736771  600           0.6515367508 
0.9929328617  0.8202360171  0.9893992933  0.9964664311  0.7891764706  0.7495291902  0.9192688500  0.8445121951  0.9452054795  0.8666666667  25.441696113  1.4183144740  2.2565736771  900           0.6352114145 
0.9924911656  0.8207870559  0.9885159011  0.9964664311  0.8108235294  0.7495291902  0.9348819497  0.8506097561  0.9563124769  0.8622222222  33.922261484  1.3623255797  2.2565736771  1200          0.6359146516 
0.9929328617  0.8236590084  0.9893992933  0.9964664311  0.8282352941  0.7476459510  0.9546839299  0.8551829268  0.9659385413  0.8681481481  42.402826855  1.2422327105  2.2565736771  1500          0.6571209590 
0.9920494695  0.8248572895  0.9876325088  0.9964664311  0.8423529412  0.7514124294  0.9619192688  0.8490853659  0.9755646057  0.8740740741  50.883392226  1.1887035759  2.2565736771  1800          0.6515650042 
0.9929328617  0.8250484204  0.9893992933  0.9964664311  0.8545882353  0.7532956685  0.9699162224  0.8551829268  0.9822288041  0.8666666667  59.363957597  1.0970516380  2.2565736771  2100          0.6550608826 
0.9933745578  0.8277567888  0.9902826855  0.9964664311  0.8677647059  0.7570621469  0.9779131759  0.8521341463  0.9848204369  0.8740740741  67.844522968  1.0842294486  2.2565736771  2400          0.6498410543 
0.9933745578  0.8224648612  0.9902826855  0.9964664311  0.8814117647  0.7532956685  0.9775323686  0.8429878049  0.9870418364  0.8711111111  76.325088339  1.0799636670  2.2565736771  2700          0.6423624126 
0.9933745578  0.8264235295  0.9902826855  0.9964664311  0.8889411765  0.7589453861  0.9859101295  0.8536585366  0.9881525361  0.8666666667  84.805653710  1.0517953976  2.2565736771  3000          0.6499744447 
0.9929328617  0.8348112803  0.9893992933  0.9964664311  0.8997647059  0.7721280603  0.9862909368  0.8582317073  0.9885227693  0.8740740741  93.286219081  1.0408064423  2.2565736771  3300          0.6459105015 
0.9924911656  0.8144502623  0.9885159011  0.9964664311  0.9077647059  0.7457627119  0.9885757807  0.8353658537  0.9922251018  0.8622222222  101.76678445  1.0234239924  2.2565736771  3600          0.6425439803 
0.9933745578  0.8210130446  0.9902826855  0.9964664311  0.9072941176  0.7457627119  0.9881949733  0.8506097561  0.9948167345  0.8666666667  110.24734982  0.8027962383  5.3972864151  3900          0.6413116320 
0.9933745578  0.8242856958  0.9902826855  0.9964664311  0.9209411765  0.7570621469  0.9900990099  0.8506097561  0.9951869678  0.8651851852  118.72791519  0.5978946454  5.3972864151  4200          0.6616339246 
0.9933745578  0.8190377360  0.9902826855  0.9964664311  0.9242352941  0.7457627119  0.9912414318  0.8506097561  0.9925953351  0.8607407407  127.20848056  0.5727158658  5.3972864151  4500          0.6587533180 
0.9933745578  0.8174836809  0.9902826855  0.9964664311  0.9256470588  0.7532956685  0.9920030465  0.8384146341  0.9944465013  0.8607407407  135.68904593  0.5619850324  5.3972864151  4800          0.6672692720 
0.9938162539  0.8299385903  0.9911660777  0.9964664311  0.9350588235  0.7514124294  0.9942878903  0.8643292683  0.9951869678  0.8740740741  141.34275618  0.5481313038  5.3972864151  5000          0.6534130013 
