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: 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/b5145aebff49b3fb6a51d433ab77cd73
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1913008900
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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: 0.5694511041907044
	lambda2: 0.6621108818243455
	last_k_epoch: 0.20248994529588413
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.502579147595572
	weight_decay: 0.0001
	worst_case_p: 0.2
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    
0.1871241485  0.0663980010  0.0253097812  0.0274261603  0.0745923739  0.0647149461  0.1187027708  0.1070528967  0.1786700659  0.1955782313  0.0000000000  4.5562868118  1.7946186066  0             1.5298182964 
0.2588489027  0.6133262300  0.7189559715  0.7067510549  0.5939144948  0.5778120185  0.5267632242  0.5554156171  0.2498406628  0.2678571429  3.0226700252  2.7655152996  2.0937752724  300           0.1509099770 
0.3548010343  0.7866435241  0.8563142631  0.8438818565  0.8189754782  0.8120184900  0.7238664987  0.7040302267  0.3439558105  0.3656462585  6.0453400504  2.4022518953  2.0937752724  600           0.1735658042 
0.3775399100  0.8097001616  0.8905879251  0.8586497890  0.8413146745  0.8248587571  0.7833753149  0.7455919395  0.3681750584  0.3869047619  9.0680100756  2.2659099233  2.0937752724  900           0.1732662861 
0.3796644054  0.8288881175  0.9090429739  0.8808016878  0.8506868661  0.8325629173  0.7991183879  0.7732997481  0.3724240493  0.3869047619  12.090680100  2.1758505634  2.0937752724  1200          0.1705884639 
0.3882699668  0.8443526565  0.9248615871  0.8966244726  0.8664783669  0.8505392912  0.8287153652  0.7858942065  0.3853834714  0.3911564626  15.113350125  2.0946811159  2.0937752724  1500          0.1666135756 
0.3952832406  0.8483882006  0.9319799631  0.9008438819  0.8752086276  0.8546481767  0.8416246851  0.7896725441  0.3917569577  0.3988095238  18.136020151  2.0197116570  2.0937752724  1800          0.1728360184 
0.3962408894  0.8610076411  0.9459530714  0.9050632911  0.8768776480  0.8618387262  0.8630352645  0.8161209068  0.3885702146  0.4039115646  21.158690176  1.9611956108  2.0937752724  2100          0.1765811165 
0.3991095002  0.8661549916  0.9520168732  0.9082278481  0.8893311080  0.8715973292  0.8693324937  0.8186397985  0.3926067559  0.4056122449  24.181360201  1.8977208320  2.0937752724  2400          0.1790628727 
0.4016597077  0.8834896470  0.9562351701  0.9198312236  0.8954936449  0.8767334361  0.8831863980  0.8539042821  0.3951561504  0.4081632653  27.204030226  1.8047840699  2.0937752724  2700          0.1804748702 
0.3999587564  0.8802591125  0.9638808331  0.9251054852  0.9037103608  0.8844375963  0.8863350126  0.8312342569  0.3960059486  0.4039115646  30.226700251  1.7383887923  2.0937752724  3000          0.1771871861 
0.4027222264  0.8831480423  0.9678354864  0.9282700422  0.9035819746  0.8823831536  0.8938916877  0.8387909320  0.3964308477  0.4090136054  33.249370277  1.6710952548  2.0937752724  3300          0.1736699939 
0.4019781110  0.8994358247  0.9720537833  0.9440928270  0.9114135319  0.8977914741  0.9105793451  0.8564231738  0.3966432972  0.4073129252  36.272040302  1.6314558065  2.0937752724  3600          0.1782376361 
0.4018718862  0.8988390468  0.9733720011  0.9504219409  0.9156502760  0.8947098100  0.9181360202  0.8513853904  0.3964308477  0.4073129252  39.294710327  1.5695889465  2.0937752724  3900          0.1753511961 
0.4049545724  0.9001148799  0.9752175059  0.9504219409  0.9211708820  0.8972778634  0.9263224181  0.8526448363  0.3957934990  0.4141156463  42.317380352  1.2187689414  5.3984646797  4200          0.2078454884 
0.4052732468  0.9050220266  0.9783812286  0.9462025316  0.9216844268  0.8998459168  0.9275818640  0.8690176322  0.3964308477  0.4141156463  45.340050377  1.0160869716  5.3984646797  4500          0.2189098994 
0.4066552527  0.9101181820  0.9781175850  0.9472573840  0.9246373090  0.9065228557  0.9260075567  0.8765743073  0.3957934990  0.4175170068  48.362720403  0.9986246616  5.3984646797  4800          0.2218593701 
0.4060179041  0.9081278703  0.9783812286  0.9419831224  0.9287456670  0.9096045198  0.9373425693  0.8727959698  0.3945188018  0.4175170068  50.377833753  0.9819552970  5.3984646797  5000          0.2219229674 
