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: [2]
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: 2
	output_dir: sweep/ablation3/outputs/19ed23bc0b91e4105d4743f700078848
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 2098980753
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	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: 0.7419102898692578
	lambda2: 0.5215383105176172
	last_k_epoch: 0.23762453204831346
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.9748462276330736
	weight_decay: 1e-06
	worst_case_p: 0.3
using augment transform
using augment transform
using normal 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    
0.0201511335  0.0805151750  0.1305035592  0.1350210970  0.0609834382  0.0606060606  0.0188916877  0.0214105793  0.0482260463  0.0459183673  0.0000000000  4.4829764366  2.1692652702  0             1.5465071201 
0.3590994960  0.6655524999  0.6944371210  0.7014767932  0.7077930415  0.7092963534  0.3680730479  0.3501259446  0.5884852348  0.5858843537  3.0226700252  2.7699026823  2.4381909370  300           0.1611260708 
0.4630037781  0.7847641411  0.8737147377  0.8628691983  0.8203877263  0.8094504366  0.4763853904  0.4496221662  0.7012959422  0.6819727891  6.0453400504  2.3693922881  2.4381909370  600           0.1821700923 
0.4754408058  0.8202933138  0.9019245979  0.8765822785  0.8345102067  0.8376990241  0.4974811083  0.4534005038  0.7388995114  0.7465986395  9.0680100756  2.2424053983  2.4381909370  900           0.1846454517 
0.5007871534  0.8281930357  0.9129976272  0.8976793249  0.8551803826  0.8454031844  0.5229848866  0.4785894207  0.7720416401  0.7414965986  12.090680100  2.1195167875  2.4381909370  1200          0.1816179951 
0.5201511332  0.8472292209  0.9209069338  0.9050632911  0.8662215946  0.8551617874  0.5403022670  0.5000000000  0.7988102826  0.7814625850  15.113350125  2.0330281051  2.4381909370  1500          0.1847815537 
0.5362090677  0.8589275467  0.9348800422  0.9208860759  0.8731544486  0.8633795583  0.5547858942  0.5176322418  0.8098576588  0.7925170068  18.136020151  1.9332009665  2.4381909370  1800          0.1856213760 
0.5414042818  0.8597635904  0.9438439230  0.9240506329  0.8829117987  0.8669748331  0.5576196474  0.5251889169  0.8236668791  0.7882653061  21.158690176  1.8680742200  2.4381909370  2100          0.1878551602 
0.5491183876  0.8700550208  0.9496440812  0.9240506329  0.8868917704  0.8808423215  0.5642317380  0.5340050378  0.8436371362  0.8052721088  24.181360201  1.7917432499  2.4381909370  2400          0.1879982877 
0.5596662466  0.8754836188  0.9580806749  0.9324894515  0.8940813968  0.8844375963  0.5727329975  0.5465994962  0.8510728702  0.8095238095  27.204030226  1.7260921292  2.4381909370  2700          0.1831283243 
0.5632871534  0.8784063966  0.9567624572  0.9229957806  0.8979329824  0.8941961993  0.5774559194  0.5491183879  0.8587210537  0.8180272109  30.226700251  1.6993186565  2.4381909370  3000          0.1842179998 
0.5717884128  0.8845509725  0.9636171896  0.9356540084  0.9040955193  0.8931689779  0.5818639798  0.5617128463  0.8687061823  0.8248299320  33.249370277  1.6798462776  2.4381909370  3300          0.1846796234 
0.5763539040  0.8867027704  0.9625626153  0.9345991561  0.9084606496  0.8972778634  0.5834382872  0.5692695214  0.8714680263  0.8282312925  36.272040302  1.6851963210  2.4381909370  3600          0.1837849927 
0.5796599493  0.8919068821  0.9665172687  0.9430379747  0.9114135319  0.9019003595  0.5862720403  0.5730478589  0.8801784576  0.8307823129  39.294710327  1.5560925206  5.3981270790  3900          0.1931696542 
0.5801322415  0.8968915936  0.9699446349  0.9472573840  0.9157786622  0.9049820236  0.5859571788  0.5743073048  0.8874017421  0.8384353741  42.317380352  1.2065636277  5.3981270790  4200          0.2187750419 
0.5771410576  0.8981078476  0.9720537833  0.9451476793  0.9148799589  0.9013867488  0.5850125945  0.5692695214  0.8882515403  0.8477891156  45.340050377  1.1848163601  5.3981270790  4500          0.2190854541 
0.5761964733  0.9005046975  0.9715264962  0.9451476793  0.9166773655  0.9085772984  0.5843828715  0.5680100756  0.8905884852  0.8477891156  48.362720403  1.1710920028  5.3981270790  4800          0.2241895660 
0.5760390425  0.8998404489  0.9736356446  0.9462025316  0.9193734754  0.9106317411  0.5853274559  0.5667506297  0.8982366688  0.8426870748  50.377833753  1.1708167875  5.3981270790  5000          0.2212574971 
