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: 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/cf92dfa6643c33399725650c70c5b687
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 502786804
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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 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    
0.1921878041  0.1821909869  0.0494699647  0.0530035336  0.3049411765  0.2862523540  0.2102056359  0.2073170732  0.1858570900  0.1985185185  0.0000000000  4.3074369431  2.0073552132  0             1.6929821968 
0.8100357888  0.8607236791  0.9991166078  0.9964664311  0.7694117647  0.7777777778  0.8823305407  0.8079268293  0.8067382451  0.8133333333  8.4805653710  1.6556502008  2.2565736771  300           0.6366092896 
0.8328092472  0.8605437762  1.0000000000  0.9964664311  0.8037647059  0.7589453861  0.9295506474  0.8262195122  0.8300629397  0.8355555556  16.961130742  1.2838832261  2.2565736771  600           0.6452010671 
0.8292914828  0.8630250969  1.0000000000  0.9964664311  0.8338823529  0.7740112994  0.9554455446  0.8185975610  0.8259903739  0.8325925926  25.441696113  1.1077238643  2.2565736771  900           0.6391043075 
0.8252186429  0.8686145278  1.0000000000  0.9964664311  0.8658823529  0.7740112994  0.9710586443  0.8353658537  0.8193261755  0.8311111111  33.922261484  0.9807806275  2.2565736771  1200          0.6285690157 
0.8202191228  0.8733196298  1.0000000000  1.0000000000  0.8903529412  0.7815442561  0.9798172125  0.8384146341  0.8167345428  0.8237037037  42.402826855  0.9001296524  2.2565736771  1500          0.6434161520 
0.8198491638  0.8695714582  1.0000000000  0.9964664311  0.9082352941  0.7890772128  0.9851485149  0.8231707317  0.8145131433  0.8251851852  50.883392226  0.8708698738  2.2565736771  1800          0.6515296380 
0.8194789306  0.8751608891  1.0000000000  0.9964664311  0.9355294118  0.7890772128  0.9878141660  0.8399390244  0.8137726768  0.8251851852  59.363957597  0.8284087423  2.2565736771  2100          0.6453092941 
0.8161457344  0.8675809178  1.0000000000  1.0000000000  0.9458823529  0.7871939736  0.9908606245  0.8155487805  0.8130322103  0.8192592593  67.844522968  0.8292499783  2.2565736771  2400          0.6393390544 
0.8152201513  0.8731406838  1.0000000000  1.0000000000  0.9515294118  0.7947269303  0.9923838538  0.8246951220  0.8111810441  0.8192592593  76.325088339  0.8263183781  2.2565736771  2700          0.6491551638 
0.8152201513  0.8731406838  1.0000000000  1.0000000000  0.9632941176  0.7947269303  0.9961919269  0.8246951220  0.8111810441  0.8192592593  84.805653710  0.8099703008  2.2565736771  3000          0.6499489029 
0.8122571883  0.8779530871  1.0000000000  1.0000000000  0.9675294118  0.7984934087  0.9961919269  0.8353658537  0.8111810441  0.8133333333  93.286219081  0.8272081653  2.2565736771  3300          0.6495220478 
0.8120720717  0.8691829445  1.0000000000  0.9964664311  0.9760000000  0.7909604520  0.9961919269  0.8201219512  0.8108108108  0.8133333333  101.76678445  0.6105544276  5.3972864151  3600          0.6661957979 
0.8113316052  0.8695234866  1.0000000000  1.0000000000  0.9778823529  0.7777777778  0.9973343488  0.8307926829  0.8093298778  0.8133333333  110.24734982  0.3955063010  5.3972864151  3900          0.6502543839 
0.8135532789  0.8683579453  1.0000000000  1.0000000000  0.9778823529  0.7834274953  0.9969535415  0.8216463415  0.8122917438  0.8148148148  118.72791519  0.3804667317  5.3972864151  4200          0.6438279422 
0.8137383955  0.8695234866  1.0000000000  1.0000000000  0.9821176471  0.7777777778  0.9984767708  0.8307926829  0.8126619770  0.8148148148  127.20848056  0.3696271922  5.3972864151  4500          0.6575087198 
0.8129976548  0.8654164661  1.0000000000  0.9964664311  0.9844705882  0.7796610169  0.9977151561  0.8201219512  0.8126619770  0.8133333333  135.68904593  0.3649015764  5.3972864151  4800          0.6404326948 
0.8133678880  0.8695234866  1.0000000000  1.0000000000  0.9830588235  0.7777777778  0.9980959634  0.8307926829  0.8134024435  0.8133333333  141.34275618  0.3599619278  5.3972864151  5000          0.6394749832 
