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: [1]
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: 3
	output_dir: sweep/ablation3/outputs/aafd972f21101be13947a7922fa79179
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 922919698
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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: 0.7010166027828918
	lambda2: 0.6269010951324223
	last_k_epoch: 0.38851977780027735
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.131347198605345
	weight_decay: 1e-06
	worst_case_p: 0.3
using augment transform
using normal 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    
0.3862098148  0.2437605881  0.1236749117  0.1519434629  0.3807058824  0.3917137476  0.2939832445  0.3185975610  0.2573121066  0.2607407407  0.0000000000  4.6803641319  2.1691374779  0             1.7312736511 
0.6615686271  0.8977893220  1.0000000000  0.9964664311  0.6564705882  0.6666666667  0.8834729627  0.8109756098  0.9303961496  0.8859259259  8.4805653710  1.5090808447  2.4361162186  300           0.1606429243 
0.6380321255  0.9090296594  1.0000000000  1.0000000000  0.6395294118  0.6365348399  0.9287890327  0.8307926829  0.9533506109  0.8962962963  16.961130742  1.0109930203  2.4361162186  600           0.1823220770 
0.6410922784  0.9120355312  1.0000000000  1.0000000000  0.6400000000  0.6421845574  0.9459253618  0.8353658537  0.9674194743  0.9007407407  25.441696113  0.8624207006  2.4361162186  900           0.1832007400 
0.6422691921  0.9100316167  1.0000000000  1.0000000000  0.6404705882  0.6440677966  0.9565879665  0.8323170732  0.9700111070  0.8977777778  33.922261484  0.7990576965  2.4361162186  1200          0.1857195393 
0.6415633097  0.9054727489  1.0000000000  1.0000000000  0.6390588235  0.6440677966  0.9702970297  0.8201219512  0.9777860052  0.8962962963  42.402826855  0.7691261051  2.4361162186  1500          0.1806669831 
0.6401511019  0.9059951819  1.0000000000  1.0000000000  0.6381176471  0.6421845574  0.9741051028  0.8231707317  0.9855609034  0.8948148148  50.883392226  0.7443863275  2.4361162186  1800          0.1819523629 
0.6413280156  0.9089867507  1.0000000000  1.0000000000  0.6385882353  0.6440677966  0.9836252856  0.8262195122  0.9837097371  0.9007407407  59.363957597  0.7297414863  2.4361162186  2100          0.1831302126 
0.6396805137  0.9053583255  1.0000000000  1.0000000000  0.6371764706  0.6421845574  0.9828636710  0.8079268293  0.9851906701  0.9081481481  67.844522968  0.7270950705  2.4361162186  2400          0.1823285683 
0.6394452196  0.9069971391  1.0000000000  1.0000000000  0.6367058824  0.6421845574  0.9889565880  0.8246951220  0.9896334691  0.8962962963  76.325088339  0.7066677209  2.4361162186  2700          0.1784773986 
0.6394452196  0.9014935257  1.0000000000  1.0000000000  0.6367058824  0.6421845574  0.9893373953  0.8170731707  0.9922251018  0.8874074074  84.805653710  0.6963208447  2.4361162186  3000          0.1820468171 
0.6401511019  0.9110621798  1.0000000000  1.0000000000  0.6381176471  0.6421845574  0.9916222391  0.8368902439  0.9914846353  0.8962962963  93.286219081  0.4359510801  5.3990564346  3300          0.2181677914 
0.6380325686  0.9049074071  1.0000000000  1.0000000000  0.6376470588  0.6384180791  0.9900990099  0.8125000000  0.9933358016  0.9022222222  101.76678445  0.3509605036  5.3990564346  3600          0.2236355305 
0.6377968314  0.9009710927  1.0000000000  1.0000000000  0.6390588235  0.6365348399  0.9927646611  0.8140243902  0.9937060348  0.8888888889  110.24734982  0.3401856768  5.3990564346  3900          0.2230276680 
0.6370905059  0.9070400479  1.0000000000  1.0000000000  0.6395294118  0.6346516008  0.9920030465  0.8292682927  0.9929655683  0.8918518519  118.72791519  0.3309875624  5.3990564346  4200          0.2171717755 
0.6377963883  0.8993608850  1.0000000000  1.0000000000  0.6409411765  0.6346516008  0.9916222391  0.8003048780  0.9922251018  0.8977777778  127.20848056  0.3249234775  5.3990564346  4500          0.2153287419 
0.6392085961  0.9114701894  1.0000000000  1.0000000000  0.6418823529  0.6365348399  0.9935262757  0.8277439024  0.9951869678  0.9066666667  135.68904593  0.3253009799  5.3990564346  4800          0.2165665809 
0.6401502157  0.9069971391  1.0000000000  1.0000000000  0.6418823529  0.6384180791  0.9939070830  0.8246951220  0.9940762680  0.8962962963  141.34275618  0.3224101533  5.3990564346  5000          0.2205085754 
