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: 4
	output_dir: sweep/ablation3/outputs/f9854f765faba79edc411cea58a90125
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1484856526
	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: 0.6171767606394463
	lambda2: 0.5293911814442921
	last_k_epoch: 0.3102645027326114
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.022572617872769
	weight_decay: 0.0001
	worst_case_p: 0.2
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    
0.0334869029  0.0452842561  0.0353282362  0.0316455696  0.0595711901  0.0616332820  0.0610831234  0.0478589421  0.0265561929  0.0263605442  0.0000000000  4.3244228363  1.7946186066  0             1.5239224434 
0.1971013670  0.5747104994  0.1832322700  0.2109704641  0.7043266145  0.7139188495  0.5053526448  0.4659949622  0.5801997026  0.5442176871  3.0226700252  2.6632099581  2.0947899818  300           0.1548781037 
0.2019790508  0.6909918493  0.1908779330  0.2130801688  0.7885479522  0.7935285054  0.6545969773  0.6246851385  0.6741024007  0.6547619048  6.0453400504  2.3721042625  2.0947899818  600           0.1772371991 
0.2101528353  0.7212322570  0.2008963881  0.2194092827  0.8083194248  0.8151001541  0.6838790932  0.6700251889  0.7168047589  0.6785714286  9.0680100756  2.2923559070  2.0947899818  900           0.1767080363 
0.2506278219  0.7381177791  0.2385974163  0.2626582278  0.8205161125  0.8294812532  0.7251259446  0.6926952141  0.7384746123  0.6921768707  12.090680100  2.2445846637  2.0947899818  1200          0.1753331629 
0.2806873587  0.7516955942  0.2670709201  0.2943037975  0.8337398896  0.8238315357  0.7471662469  0.7229219144  0.7646059061  0.7083333333  15.113350125  2.2067863349  2.0947899818  1500          0.1758295655 
0.2962446922  0.7701805282  0.2802530978  0.3122362869  0.8464501220  0.8402670776  0.7789672544  0.7304785894  0.7881878054  0.7397959184  18.136020151  2.1447539282  2.0947899818  1800          0.1744784411 
0.3158885009  0.7783398426  0.3016082257  0.3301687764  0.8551803826  0.8474576271  0.7909319899  0.7418136020  0.7926492458  0.7457482993  21.158690176  2.0896769949  2.0947899818  2100          0.1747890019 
0.3331593785  0.7899981688  0.3192723438  0.3470464135  0.8651945051  0.8454031844  0.8104534005  0.7720403023  0.8170809433  0.7525510204  24.181360201  2.0400612942  2.0947899818  2400          0.1770722294 
0.3383009840  0.8095952053  0.3253361455  0.3512658228  0.8727692900  0.8602978942  0.8258816121  0.7972292191  0.8130444020  0.7712585034  27.204030226  2.0009364017  2.0947899818  2700          0.1753974827 
0.3459474814  0.8163885084  0.3343000264  0.3575949367  0.8835537296  0.8705701079  0.8387909320  0.8047858942  0.8370512003  0.7738095238  30.226700251  1.9542419684  2.0947899818  3000          0.1741059923 
0.3612406152  0.8228786254  0.3511732138  0.3713080169  0.8859930671  0.8726245506  0.8346977330  0.8060453401  0.8396005949  0.7899659864  33.249370277  1.9121135529  2.0947899818  3300          0.1757258248 
0.3704696691  0.8255427999  0.3580279462  0.3829113924  0.8958788034  0.8787878788  0.8602015113  0.7959697733  0.8508604207  0.8018707483  36.272040302  1.5527864325  5.4009556770  3600          0.1984168474 
0.3728428783  0.8373914231  0.3596098075  0.3860759494  0.8976762100  0.8803287108  0.8702770781  0.8299748111  0.8646696410  0.8018707483  39.294710327  1.1366774789  5.4009556770  3900          0.2193029602 
0.3773253749  0.8432435620  0.3643553915  0.3902953586  0.8978045962  0.8911145352  0.8683879093  0.8324937028  0.8701933291  0.8061224490  42.317380352  1.1065937692  5.4009556770  4200          0.2216205192 
0.3800939103  0.8508373977  0.3677827577  0.3924050633  0.9052509950  0.8885464818  0.8869647355  0.8450881612  0.8740174209  0.8188775510  45.340050377  1.0836813239  5.4009556770  4500          0.2202463762 
0.3848401895  0.8594754878  0.3720010546  0.3976793249  0.9111567595  0.8967642527  0.8920025189  0.8576826196  0.8844274485  0.8239795918  48.362720403  1.0645399831  5.4009556770  4800          0.2184109060 
0.3885317555  0.8569267930  0.3751647772  0.4018987342  0.9139812556  0.8936825886  0.9005037783  0.8488664987  0.8829403017  0.8282312925  50.377833753  1.0504425892  5.4009556770  5000          0.2177739894 
