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: TerraIncognita
	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/52152d0bed140f491e82b4c876660409
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 95752158
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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: 0.8610090196552951
	lambda2: 0.5777772877463595
	last_k_epoch: 0.32350558703299503
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.866557071912062
	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    
0.3247211161  0.0612718143  0.3150540469  0.3343881857  0.0364616767  0.0385208012  0.0771410579  0.0755667506  0.0762693860  0.0697278912  0.0000000000  5.2109923363  2.0074815750  0             1.4469323158 
0.2390254198  0.6012139666  0.2312153968  0.2468354430  0.7267941969  0.7257318952  0.5264483627  0.5251889169  0.5755258126  0.5527210884  3.0226700252  2.8484347653  2.2552723885  300           0.1597994391 
0.1804890420  0.6928176583  0.1711046665  0.1898734177  0.8043394531  0.7904468413  0.6426322418  0.6536523929  0.6681538135  0.6343537415  6.0453400504  2.5413312062  2.2552723885  600           0.1825240993 
0.2243909777  0.7170543473  0.2188241497  0.2299578059  0.8224419053  0.8068823832  0.7005667506  0.6750629723  0.7046951349  0.6692176871  9.0680100756  2.4269176165  2.2552723885  900           0.1823116302 
0.2892556351  0.7551920417  0.2852623253  0.2932489451  0.8304018488  0.8356445814  0.7386649874  0.7267002519  0.7374123646  0.7032312925  12.090680100  2.3573615201  2.2552723885  1200          0.1818872436 
0.3288078693  0.7589120646  0.3211178487  0.3364978903  0.8527410451  0.8397534669  0.7585012594  0.7405541562  0.7660930529  0.6964285714  15.113350125  2.3162644807  2.2552723885  1500          0.1818478274 
0.3546486920  0.7863042086  0.3443184814  0.3649789030  0.8639106432  0.8572162301  0.7729848866  0.7670025189  0.7799022732  0.7346938776  18.136020151  2.2355732501  2.2552723885  1800          0.1815041685 
0.3802260102  0.7834620033  0.3659372528  0.3945147679  0.8716138144  0.8592706728  0.7950251889  0.7632241814  0.7973231358  0.7278911565  21.158690176  2.1600995489  2.2552723885  2100          0.1788332303 
0.3969694616  0.8042746210  0.3836013709  0.4103375527  0.8759789447  0.8654340010  0.8098236776  0.7846347607  0.8141066497  0.7627551020  24.181360201  2.1214754903  2.2552723885  2400          0.1774011024 
0.4121310518  0.8198804278  0.3981017664  0.4261603376  0.8835537296  0.8685156651  0.8290302267  0.8224181360  0.8194178883  0.7687074830  27.204030226  2.0609957751  2.2552723885  2700          0.1750406059 
0.4354669826  0.8234789391  0.4184023201  0.4525316456  0.8886891770  0.8828967643  0.8444584383  0.8035264484  0.8355640535  0.7840136054  30.226700251  1.9913186904  2.2552723885  3000          0.1758993395 
0.4469374239  0.8316701170  0.4265752702  0.4672995781  0.8957504173  0.8885464818  0.8557934509  0.8198992443  0.8495857234  0.7865646259  33.249370277  1.9643190014  2.2552723885  3300          0.1762634683 
0.4452233237  0.8334454992  0.4263116267  0.4641350211  0.9021697265  0.8870056497  0.8727959698  0.8148614610  0.8591459528  0.7984693878  36.272040302  1.5208740815  5.3961586952  3600          0.2050028570 
0.4432457189  0.8482012310  0.4244661218  0.4620253165  0.9039671331  0.8916281459  0.8806675063  0.8400503778  0.8644571914  0.8129251701  39.294710327  1.2838630497  5.3961586952  3900          0.2181323202 
0.4429822144  0.8467075001  0.4228842605  0.4630801688  0.9094877391  0.8993323061  0.8879093199  0.8287153652  0.8706182282  0.8120748299  42.317380352  1.2606762644  5.3961586952  4200          0.2231897902 
0.4407409661  0.8478132793  0.4205114685  0.4609704641  0.9142380280  0.8900873138  0.8825566751  0.8438287154  0.8710431273  0.8095238095  45.340050377  1.2421714703  5.3961586952  4500          0.2228881923 
0.4388951831  0.8513787510  0.4189296072  0.4588607595  0.9147515727  0.8977914741  0.8957808564  0.8425692695  0.8744423199  0.8137755102  48.362720403  1.2320897182  5.3961586952  4800          0.2218719276 
0.4374451436  0.8580930892  0.4160295281  0.4588607595  0.9156502760  0.8972778634  0.8998740554  0.8564231738  0.8772041640  0.8205782313  50.377833753  1.2153697342  5.3961586952  5000          0.2235203695 
