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: 4
	output_dir: sweep/ablation3/outputs/56cc4a0563d338a48710e168dc79c28d
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 397377531
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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: 0.5122476832929141
	lambda2: 0.9892716333303577
	last_k_epoch: 0.2899069879248226
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.19589595208549
	weight_decay: 0.0001
	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    
0.1462014134  0.1531923583  0.1475265018  0.1448763251  0.2075294118  0.1902071563  0.1009139375  0.0960365854  0.1928915217  0.1733333333  0.0000000000  4.1702489853  2.1691374779  0             1.6713645458 
0.9558303882  0.8047180242  0.9575971731  0.9540636042  0.7614117647  0.7514124294  0.8659558264  0.8079268293  0.9026286561  0.8548148148  8.4805653710  1.8549732025  2.4372453690  300           0.6450972541 
0.9743816250  0.8285717491  0.9770318021  0.9717314488  0.7891764706  0.7645951036  0.9063214014  0.8292682927  0.9348389485  0.8918518519  16.961130742  1.3879979424  2.4372453690  600           0.6520073263 
0.9673144871  0.8227420266  0.9734982332  0.9611307420  0.8014117647  0.7683615819  0.9226961158  0.8109756098  0.9540910774  0.8888888889  25.441696113  1.2482123264  2.4372453690  900           0.6577475580 
0.9677561833  0.8273489961  0.9779151943  0.9575971731  0.8164705882  0.7702448211  0.9394516375  0.8140243902  0.9552017771  0.8977777778  33.922261484  1.1243586894  2.4372453690  1200          0.6380909793 
0.9690812716  0.8263899476  0.9770318021  0.9611307420  0.8418823529  0.7702448211  0.9512566641  0.8170731707  0.9692706405  0.8918518519  42.402826855  1.0247430909  2.4372453690  1500          0.6384355752 
0.9695229677  0.8307719874  0.9779151943  0.9611307420  0.8607058824  0.7683615819  0.9676313785  0.8246951220  0.9751943725  0.8992592593  50.883392226  0.9302613411  2.4372453690  1800          0.6404885904 
0.9699646638  0.8296636578  0.9787985866  0.9611307420  0.8828235294  0.7740112994  0.9733434882  0.8216463415  0.9837097371  0.8933333333  59.363957597  0.8908691738  2.4372453690  2100          0.6533594275 
0.9699646638  0.8298844536  0.9787985866  0.9611307420  0.8997647059  0.7683615819  0.9790555979  0.8353658537  0.9863013699  0.8859259259  67.844522968  0.8638200957  2.4372453690  2400          0.6489555724 
0.9699646638  0.8300716674  0.9787985866  0.9611307420  0.9148235294  0.7740112994  0.9866717441  0.8125000000  0.9863013699  0.9037037037  76.325088339  0.8372632527  2.4372453690  2700          0.6395499579 
0.9704063599  0.8264666552  0.9796819788  0.9611307420  0.9275294118  0.7721280603  0.9862909368  0.8109756098  0.9914846353  0.8962962963  84.805653710  0.8333440044  2.4372453690  3000          0.6359554013 
0.9708480561  0.8275983977  0.9805653710  0.9611307420  0.9355294118  0.7645951036  0.9927646611  0.8307926829  0.9896334691  0.8874074074  93.286219081  0.8324448087  2.4372453690  3300          0.6355597496 
0.9743816250  0.8303977766  0.9805653710  0.9681978799  0.9463529412  0.7702448211  0.9908606245  0.8231707317  0.9944465013  0.8977777778  101.76678445  0.7818239774  5.3970270157  3600          0.6509195733 
0.9752650172  0.8344760611  0.9823321555  0.9681978799  0.9491764706  0.7777777778  0.9893373953  0.8323170732  0.9937060348  0.8933333333  110.24734982  0.5220322013  5.3970270157  3900          0.6422984942 
0.9779151939  0.8268070672  0.9840989399  0.9717314488  0.9571764706  0.7683615819  0.9931454684  0.8231707317  0.9948167345  0.8888888889  118.72791519  0.4980699929  5.3970270157  4200          0.6361028830 
0.9779151939  0.8344628172  0.9840989399  0.9717314488  0.9618823529  0.7702448211  0.9923838538  0.8353658537  0.9944465013  0.8977777778  127.20848056  0.4866483957  5.3970270157  4500          0.6482685335 
0.9779151939  0.8274062078  0.9840989399  0.9717314488  0.9661176471  0.7702448211  0.9950495050  0.8201219512  0.9962976675  0.8918518519  135.68904593  0.4768629291  5.3970270157  4800          0.6358380310 
0.9779151939  0.8340721855  0.9840989399  0.9717314488  0.9632941176  0.7871939736  0.9935262757  0.8231707317  0.9955572010  0.8918518519  141.34275618  0.4749107641  5.3970270157  5000          0.6379798079 
