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: 2
	output_dir: sweep/ablation3/outputs/3b031c961a4b898dbabc3157c493085b
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 396676159
	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: 0.5439617198173775
	lambda2: 0.5509403872292429
	last_k_epoch: 0.38252238504986713
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.920147743151585
	weight_decay: 1e-06
	worst_case_p: 0.3
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    
0.2416207988  0.3710851263  0.3365724382  0.3533568905  0.4155294118  0.3879472693  0.3507235339  0.3719512195  0.2476860422  0.2355555556  0.0000000000  5.9254703522  2.1691374779  0             1.5028946400 
0.8215165847  0.8549360385  1.0000000000  1.0000000000  0.8155294118  0.7401129944  0.8796648896  0.8246951220  0.8104405776  0.8325925926  8.4805653710  1.4965800122  2.4361162186  300           0.6540934706 
0.8324379170  0.8658939744  1.0000000000  0.9964664311  0.8296470588  0.7551789077  0.9371667936  0.8460365854  0.8352462051  0.8296296296  16.961130742  1.1424538231  2.4361162186  600           0.6454185716 
0.8250316065  0.8712268229  1.0000000000  1.0000000000  0.8583529412  0.7645951036  0.9600152323  0.8490853659  0.8293224732  0.8207407407  25.441696113  0.9611531250  2.4361162186  900           0.6414804681 
0.8226253647  0.8674603445  1.0000000000  1.0000000000  0.8955294118  0.7532956685  0.9737242955  0.8490853659  0.8230285080  0.8222222222  33.922261484  0.8486443086  2.4361162186  1200          0.6440628894 
0.8226248162  0.8707186928  1.0000000000  1.0000000000  0.9176470588  0.7645951036  0.9840060929  0.8475609756  0.8259903739  0.8192592593  42.402826855  0.7839492965  2.4361162186  1500          0.6596717811 
0.8235506735  0.8693435837  1.0000000000  1.0000000000  0.9411764706  0.7589453861  0.9920030465  0.8490853659  0.8263606072  0.8207407407  50.883392226  0.7577743812  2.4361162186  1800          0.6415609296 
0.8233655569  0.8771454378  1.0000000000  1.0000000000  0.9557647059  0.7777777778  0.9920030465  0.8536585366  0.8259903739  0.8207407407  59.363957597  0.7501725755  2.4361162186  2100          0.6406640244 
0.8220691921  0.8717952396  1.0000000000  1.0000000000  0.9647058824  0.7815442561  0.9935262757  0.8338414634  0.8263606072  0.8177777778  67.844522968  0.7408733237  2.4361162186  2400          0.6305695685 
0.8222543087  0.8673110634  1.0000000000  1.0000000000  0.9774117647  0.7589453861  0.9961919269  0.8429878049  0.8267308404  0.8177777778  76.325088339  0.7395657917  2.4361162186  2700          0.6465413237 
0.8226248162  0.8698517138  1.0000000000  1.0000000000  0.9788235294  0.7589453861  0.9965727342  0.8506097561  0.8259903739  0.8192592593  84.805653710  0.7234256734  2.4361162186  3000          0.6556443612 
0.8237355159  0.8727215483  1.0000000000  1.0000000000  0.9821176471  0.7721280603  0.9977151561  0.8460365854  0.8282117734  0.8192592593  93.286219081  0.4953664114  5.3990564346  3300          0.6466082740 
0.8266982046  0.8689847348  1.0000000000  1.0000000000  0.9877647059  0.7532956685  0.9961919269  0.8536585366  0.8296927064  0.8237037037  101.76678445  0.3704037361  5.3990564346  3600          0.6325311565 
0.8292903859  0.8673886998  1.0000000000  0.9964664311  0.9844705882  0.7627118644  0.9973343488  0.8429878049  0.8319141059  0.8266666667  110.24734982  0.3533359594  5.3990564346  3900          0.6549830500 
0.8298460100  0.8746344523  1.0000000000  1.0000000000  0.9896470588  0.7702448211  0.9973343488  0.8536585366  0.8315438726  0.8281481481  118.72791519  0.3476209697  5.3990564346  4200          0.6449981276 
0.8291049950  0.8744851711  1.0000000000  1.0000000000  0.9901176471  0.7758945386  0.9980959634  0.8475609756  0.8330248056  0.8251851852  127.20848056  0.3437928917  5.3990564346  4500          0.6496749083 
0.8318822928  0.8713464392  1.0000000000  1.0000000000  0.9920000000  0.7664783427  0.9984767708  0.8475609756  0.8356164384  0.8281481481  135.68904593  0.3376011022  5.3990564346  4800          0.6435704915 
0.8309564355  0.8711848430  1.0000000000  0.9964664311  0.9896470588  0.7664783427  0.9984767708  0.8506097561  0.8352462051  0.8266666667  141.34275618  0.3361820470  5.3990564346  5000          0.6439666975 
