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/fed6ad2b66a253d5af19d9b22917a9c0
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1501485666
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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: 0.6880433961757358
	lambda2: 0.9840350138898164
	last_k_epoch: 0.33648211095401626
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3.599417945900826
	weight_decay: 0.0001
	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    
0.1214664310  0.3152462500  0.1298586572  0.1130742049  0.3374117647  0.3126177024  0.4101294745  0.3871951220  0.2554609404  0.2459259259  0.0000000000  3.7417860031  2.0073552132  0             1.5913944244 
0.9840989394  0.7949746602  0.9858657244  0.9823321555  0.7435294118  0.7344632768  0.8514851485  0.7926829268  0.8981858571  0.8577777778  8.4805653710  1.9841941794  2.2565736771  300           0.6664940818 
0.9889575967  0.8161751103  0.9920494700  0.9858657244  0.7896470588  0.7589453861  0.9067022087  0.8140243902  0.9337282488  0.8755555556  16.961130742  1.5072389841  2.2565736771  600           0.6482446257 
0.9902826850  0.8145311038  0.9911660777  0.9893992933  0.8094117647  0.7570621469  0.9284082254  0.8109756098  0.9459459459  0.8755555556  25.441696113  1.4045933751  2.2565736771  900           0.6337751158 
0.9924911656  0.8274623605  0.9920494700  0.9929328622  0.8240000000  0.7777777778  0.9485910129  0.8216463415  0.9581636431  0.8829629630  33.922261484  1.3237727608  2.2565736771  1200          0.6453890045 
0.9929328617  0.8191482423  0.9929328622  0.9929328622  0.8362352941  0.7495291902  0.9581111957  0.8338414634  0.9655683080  0.8740740741  42.402826855  1.2117386810  2.2565736771  1500          0.6375500059 
0.9938162539  0.8249942837  0.9946996466  0.9929328622  0.8498823529  0.7702448211  0.9706778370  0.8262195122  0.9763050722  0.8785185185  50.883392226  1.1029020147  2.2565736771  1800          0.6335930451 
0.9920494695  0.8130558743  0.9946996466  0.9893992933  0.8677647059  0.7514124294  0.9744859101  0.8018292683  0.9825990374  0.8859259259  59.363957597  1.0410627164  2.2565736771  2100          0.6249464997 
0.9920494695  0.8171484617  0.9946996466  0.9893992933  0.8889411765  0.7589453861  0.9809596344  0.8125000000  0.9848204369  0.8800000000  67.844522968  1.0211188809  2.2565736771  2400          0.6331488856 
0.9911660772  0.8247264452  0.9929328622  0.9893992933  0.8964705882  0.7664783427  0.9859101295  0.8262195122  0.9903739356  0.8814814815  76.325088339  1.0028301418  2.2565736771  2700          0.6392916695 
0.9916077734  0.8184765281  0.9938162544  0.9893992933  0.9148235294  0.7551789077  0.9893373953  0.8246951220  0.9922251018  0.8755555556  84.805653710  0.9912632229  2.2565736771  3000          0.6444704088 
0.9907243811  0.8199701945  0.9920494700  0.9893992933  0.9270588235  0.7702448211  0.9897182026  0.8170731707  0.9940762680  0.8725925926  93.286219081  0.9627730779  2.2565736771  3300          0.6328270674 
0.9893992928  0.8181361161  0.9893992933  0.9893992933  0.9289411765  0.7589453861  0.9939070830  0.8125000000  0.9922251018  0.8829629630  101.76678445  0.6393976763  5.3972864151  3600          0.6248240646 
0.9902826850  0.8195541339  0.9911660777  0.9893992933  0.9369411765  0.7645951036  0.9939070830  0.8155487805  0.9951869678  0.8785185185  110.24734982  0.5735230905  5.3972864151  3900          0.6252406979 
0.9898409889  0.8235333570  0.9902826855  0.9893992933  0.9472941176  0.7645951036  0.9904798172  0.8185975610  0.9955572010  0.8874074074  118.72791519  0.5550023260  5.3972864151  4200          0.6410655189 
0.9898409889  0.8172834400  0.9902826855  0.9893992933  0.9543529412  0.7532956685  0.9939070830  0.8170731707  0.9966679008  0.8814814815  127.20848056  0.5355276665  5.3972864151  4500          0.6304596726 
0.9916077734  0.8309334535  0.9902826855  0.9929328622  0.9614117647  0.7777777778  0.9961919269  0.8231707317  0.9940762680  0.8918518519  135.68904593  0.5312009503  5.3972864151  4800          0.6236549886 
0.9920494695  0.8234841963  0.9911660777  0.9929328622  0.9567058824  0.7702448211  0.9939070830  0.8231707317  0.9974083673  0.8770370370  141.34275618  0.5178536253  5.3972864151  5000          0.6143595135 
