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: 0
	output_dir: sweep/ablation3/outputs/cb60867207d8da8321fbdbfbec544e5e
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1605385051
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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: 0.5
	lambda2: 0.5
	last_k_epoch: 0.25
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3
	weight_decay: 0.0
	worst_case_p: 0.3333333333333333
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    
0.1966281349  0.1870998948  0.2464664311  0.3003533569  0.0870588235  0.0734463277  0.1816450876  0.1875000000  0.2080710848  0.1851851852  0.0000000000  4.1674861908  2.3337798119  0             1.5136942863 
0.7948526605  0.8452395871  1.0000000000  0.9964664311  0.7943529412  0.7419962335  0.8918507235  0.7972560976  0.7956312477  0.7940740741  8.4805653710  1.4340468129  2.5977830887  300           0.6354921667 
0.8274378484  0.8604958045  1.0000000000  1.0000000000  0.8249411765  0.7476459510  0.9386900228  0.8338414634  0.8356164384  0.8192592593  16.961130742  1.0571654526  2.5977830887  600           0.6271643488 
0.8170704947  0.8660555706  1.0000000000  1.0000000000  0.8705882353  0.7551789077  0.9645849200  0.8429878049  0.8193261755  0.8148148148  25.441696113  0.8766393095  2.5977830887  900           0.6447771080 
0.8150342119  0.8689130901  1.0000000000  0.9964664311  0.9025882353  0.7627118644  0.9763899467  0.8475609756  0.8152536098  0.8148148148  33.922261484  0.7916292236  2.5977830887  1200          0.6446544131 
0.8089239921  0.8717349529  1.0000000000  1.0000000000  0.9218823529  0.7645951036  0.9840060929  0.8506097561  0.8104405776  0.8074074074  42.402826855  0.7506909289  2.5977830887  1500          0.6549502746 
0.8133681623  0.8739770410  1.0000000000  1.0000000000  0.9421176471  0.7758945386  0.9893373953  0.8460365854  0.8119215106  0.8148148148  50.883392226  0.7233386709  2.5977830887  1800          0.6386444489 
0.8135524562  0.8669225496  1.0000000000  1.0000000000  0.9529411765  0.7608286252  0.9931454684  0.8399390244  0.8167345428  0.8103703704  59.363957597  0.6973908509  2.5977830887  2100          0.6443717853 
0.8154038966  0.8726499036  1.0000000000  0.9964664311  0.9642352941  0.7815442561  0.9927646611  0.8399390244  0.8189559422  0.8118518519  67.844522968  0.6956246426  2.5977830887  2400          0.6458259050 
0.8163297540  0.8745331427  1.0000000000  0.9964664311  0.9727058824  0.7871939736  0.9946686976  0.8399390244  0.8193261755  0.8133333333  76.325088339  0.6897271788  2.5977830887  2700          0.6400905625 
0.8146631559  0.8708862807  1.0000000000  0.9964664311  0.9764705882  0.7777777778  0.9950495050  0.8384146341  0.8189559422  0.8103703704  84.805653710  0.6833872873  2.5977830887  3000          0.6210120900 
0.8142931969  0.8677772136  1.0000000000  0.9964664311  0.9821176471  0.7608286252  0.9965727342  0.8460365854  0.8167345428  0.8118518519  93.286219081  0.6741127664  2.5977830887  3300          0.6392313242 
0.8146637044  0.8705694116  1.0000000000  1.0000000000  0.9830588235  0.7702448211  0.9961919269  0.8414634146  0.8159940763  0.8133333333  101.76678445  0.6968021004  2.5977830887  3600          0.6429069289 
0.8137378470  0.8655177757  1.0000000000  1.0000000000  0.9891764706  0.7627118644  0.9992383854  0.8338414634  0.8156238430  0.8118518519  110.24734982  0.5164778084  5.3947153091  3900          0.6504754376 
0.8133673395  0.8740669925  1.0000000000  1.0000000000  0.9901176471  0.7853107345  0.9988575781  0.8368902439  0.8163643095  0.8103703704  118.72791519  0.3487437278  5.3947153091  4200          0.6513928811 
0.8133670653  0.8717829246  1.0000000000  0.9964664311  0.9896470588  0.7758945386  0.9992383854  0.8429878049  0.8178452425  0.8088888889  127.20848056  0.3344185534  5.3947153091  4500          0.6416769282 
0.8137375728  0.8736181921  1.0000000000  1.0000000000  0.9896470588  0.7702448211  0.9992383854  0.8506097561  0.8171047760  0.8103703704  135.68904593  0.3280144413  5.3947153091  4800          0.6424680456 
0.8135524562  0.8670421659  1.0000000000  1.0000000000  0.9910588235  0.7627118644  0.9984767708  0.8384146341  0.8167345428  0.8103703704  141.34275618  0.3259015058  5.3947153091  5000          0.6407575846 
