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/784774d1a58ee86855d1c629a2122736
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 2014778025
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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: 0.5
	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    
0.2157006320  0.2848136648  0.5600706714  0.5795053004  0.1214117647  0.0828625235  0.1949733435  0.1920731707  0.2165864495  0.2148148148  0.0000000000  3.3234586716  2.3337798119  0             1.5979721546 
0.8389205640  0.8660861924  1.0000000000  1.0000000000  0.7891764706  0.7796610169  0.9006092917  0.8185975610  0.8289522399  0.8488888889  8.4805653710  1.4197840583  2.5977830887  300           0.6414760200 
0.8316988217  0.8647407481  1.0000000000  1.0000000000  0.8385882353  0.7664783427  0.9478293983  0.8277439024  0.8263606072  0.8370370370  16.961130742  1.0515918005  2.5977830887  600           0.6364259656 
0.8309578067  0.8659962409  1.0000000000  1.0000000000  0.8672941176  0.7702448211  0.9642041127  0.8277439024  0.8278415402  0.8340740741  25.441696113  0.8816273757  2.5977830887  900           0.6327873413 
0.8265139108  0.8689856917  1.0000000000  1.0000000000  0.9087058824  0.7853107345  0.9790555979  0.8216463415  0.8248796742  0.8281481481  33.922261484  0.7897421551  2.5977830887  1200          0.6336542201 
0.8296619903  0.8703904656  1.0000000000  1.0000000000  0.9232941176  0.7834274953  0.9878141660  0.8277439024  0.8252499074  0.8340740741  42.402826855  0.7412807159  2.5977830887  1500          0.6372199591 
0.8252183686  0.8739473762  1.0000000000  1.0000000000  0.9355294118  0.7834274953  0.9889565880  0.8384146341  0.8208071085  0.8296296296  50.883392226  0.7156591598  2.5977830887  1800          0.6263153998 
0.8222554057  0.8688957402  1.0000000000  1.0000000000  0.9515294118  0.7758945386  0.9935262757  0.8307926829  0.8208071085  0.8237037037  59.363957597  0.6926643242  2.5977830887  2100          0.6303360621 
0.8244779021  0.8639637206  1.0000000000  1.0000000000  0.9609411765  0.7702448211  0.9939070830  0.8216463415  0.8193261755  0.8296296296  67.844522968  0.6935307709  2.5977830887  2400          0.6264940413 
0.8252183686  0.8708689309  1.0000000000  1.0000000000  0.9684705882  0.7909604520  0.9954303123  0.8216463415  0.8208071085  0.8296296296  76.325088339  0.6871180298  2.5977830887  2700          0.6420729852 
0.8228113040  0.8745751226  1.0000000000  1.0000000000  0.9769411765  0.7853107345  0.9965727342  0.8384146341  0.8189559422  0.8266666667  84.805653710  0.6762508482  2.5977830887  3000          0.6313712239 
0.8220705633  0.8710775417  1.0000000000  1.0000000000  0.9807058824  0.7702448211  0.9965727342  0.8429878049  0.8189559422  0.8251851852  93.286219081  0.6710895522  2.5977830887  3300          0.6226367029 
0.8205893561  0.8724229859  1.0000000000  1.0000000000  0.9887058824  0.7834274953  0.9973343488  0.8338414634  0.8174750093  0.8237037037  101.76678445  0.6795933100  2.5977830887  3600          0.6376499232 
0.8183674081  0.8718851910  1.0000000000  1.0000000000  0.9868235294  0.7909604520  0.9980959634  0.8246951220  0.8159940763  0.8207407407  110.24734982  0.5218358606  5.3947153091  3900          0.6463072109 
0.8211449802  0.8698823355  1.0000000000  1.0000000000  0.9915294118  0.7834274953  0.9984767708  0.8262195122  0.8171047760  0.8251851852  118.72791519  0.3461210189  5.3947153091  4200          0.6321981716 
0.8218854467  0.8746947389  1.0000000000  1.0000000000  0.9910588235  0.7871939736  0.9980959634  0.8368902439  0.8185857090  0.8251851852  127.20848056  0.3379610810  5.3947153091  4500          0.6388547150 
0.8207744727  0.8683876101  1.0000000000  1.0000000000  0.9924705882  0.7758945386  0.9984767708  0.8292682927  0.8178452425  0.8237037037  135.68904593  0.3291970122  5.3947153091  4800          0.6325956059 
0.8211449802  0.8683876101  1.0000000000  1.0000000000  0.9905882353  0.7758945386  0.9992383854  0.8292682927  0.8171047760  0.8251851852  141.34275618  0.3273814856  5.3947153091  5000          0.6294361496 
