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: 1
	output_dir: sweep/ablation3/outputs/f0746dd2ec713f64c19cb080f809b34b
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1295575529
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	trial_seed: 2
	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: 0.6109302038716249
	lambda2: 0.5117744391412766
	last_k_epoch: 0.31317984427858747
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.002688876693512
	weight_decay: 1e-06
	worst_case_p: 0.25
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    
0.1536523929  0.2434157336  0.4495122594  0.4546413502  0.0473745025  0.0400616333  0.1561712846  0.1511335013  0.2247716167  0.2355442177  0.0000000000  4.0921211243  2.0074815750  0             1.6394810677 
0.3724811081  0.7189588282  0.8030582652  0.7964135021  0.7374502504  0.7057010786  0.3759445844  0.3690176322  0.6494582537  0.6547619048  3.0226700252  2.7180259752  2.2580189705  300           0.1525033959 
0.4554471030  0.8057213687  0.8829422621  0.8649789030  0.8301450764  0.8166409861  0.4700881612  0.4408060453  0.7323135755  0.7355442177  6.0453400504  2.3896187111  2.2580189705  600           0.1769331479 
0.4856738033  0.8240978551  0.9111521223  0.8902953586  0.8514571832  0.8243451464  0.4952770781  0.4760705290  0.7697046951  0.7576530612  9.0680100756  2.2431604060  2.2580189705  900           0.1727280188 
0.4987405539  0.8398897528  0.9240706565  0.8934599156  0.8641674156  0.8489984592  0.5125944584  0.4848866499  0.7930741449  0.7772108844  12.090680100  2.1539847406  2.2580189705  1200          0.1745856857 
0.5198362718  0.8517869131  0.9390983390  0.9124472574  0.8763641032  0.8546481767  0.5308564232  0.5088161209  0.8068833652  0.7882653061  15.113350125  2.0483062971  2.2580189705  1500          0.1725306892 
0.5319584380  0.8577194858  0.9464803586  0.9082278481  0.8859930671  0.8664612224  0.5425062972  0.5214105793  0.8264287232  0.7984693878  18.136020151  1.9617303101  2.2580189705  1800          0.1736628024 
0.5396725438  0.8630152750  0.9517532296  0.9156118143  0.8904865836  0.8664612224  0.5503778338  0.5289672544  0.8349267049  0.8069727891  21.158690176  1.8933960243  2.2580189705  2100          0.1726434541 
0.5406171282  0.8710119264  0.9622989718  0.9240506329  0.8992168443  0.8777606574  0.5522670025  0.5289672544  0.8457616316  0.8112244898  24.181360201  1.8002838031  2.2580189705  2400          0.1799484754 
0.5445528965  0.8780105409  0.9636171896  0.9303797468  0.9055077674  0.8839239856  0.5563602015  0.5327455919  0.8599957510  0.8197278912  27.204030226  1.7226738795  2.2580189705  2700          0.1767630736 
0.5483312340  0.8860050473  0.9665172687  0.9398734177  0.9087174220  0.8890600924  0.5626574307  0.5340050378  0.8672190355  0.8290816327  30.226700251  1.6665772927  2.2580189705  3000          0.1747539520 
0.5519521408  0.8913045350  0.9704719220  0.9409282700  0.9146231865  0.8962506420  0.5648614610  0.5390428212  0.8710431273  0.8367346939  33.249370277  1.6281237674  2.2580189705  3300          0.1742693806 
0.5560453398  0.8930201033  0.9715264962  0.9419831224  0.9157786622  0.8977914741  0.5680100756  0.5440806045  0.8782664117  0.8392857143  36.272040302  1.3391154778  5.3947548866  3600          0.1962094148 
0.5532115866  0.9006722026  0.9746902188  0.9514767932  0.9220695853  0.9019003595  0.5661209068  0.5403022670  0.8854896962  0.8486394558  39.294710327  1.0742300455  5.3947548866  3900          0.2148475893 
0.5533690174  0.8991591673  0.9752175059  0.9472573840  0.9242521505  0.9049820236  0.5676952141  0.5390428212  0.8920756320  0.8452380952  42.317380352  1.0565482271  5.3947548866  4200          0.2168787758 
0.5521095715  0.9046277136  0.9783812286  0.9493670886  0.9288740532  0.9065228557  0.5676952141  0.5365239295  0.8971744211  0.8579931973  45.340050377  1.0476283443  5.3947548866  4500          0.2138924050 
0.5522670022  0.9082557054  0.9815449512  0.9483122363  0.9300295288  0.9116589625  0.5680100756  0.5365239295  0.8967495220  0.8647959184  48.362720403  1.0306045473  5.3947548866  4800          0.2136096692 
0.5516372793  0.9038071494  0.9778539415  0.9514767932  0.9311850045  0.9096045198  0.5667506297  0.5365239295  0.9012109624  0.8503401361  50.377833753  1.0240519896  5.3947548866  5000          0.2137941039 
