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: 1
	output_dir: sweep/ablation3/outputs/4cbe68e29a1f47b799678dbdcc5a58e8
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1830790474
	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: 0.6109302038716249
	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 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    
0.0411228067  0.1415418303  0.2008963881  0.2215189873  0.0559763769  0.0570107858  0.1193324937  0.1460957179  0.0388782664  0.0433673469  0.0000000000  4.3130059242  2.0074815750  0             1.6201918125 
0.3249402213  0.7047937330  0.7925125231  0.7816455696  0.7506740275  0.7231638418  0.6268891688  0.6095717884  0.3207988103  0.3290816327  3.0226700252  2.7184968360  2.2580189705  300           0.1575047795 
0.3861433035  0.7980219395  0.8771421039  0.8502109705  0.8306586211  0.8171545968  0.7421284635  0.7267002519  0.3879328659  0.3843537415  6.0453400504  2.3080323140  2.2580189705  600           0.1825151952 
0.4053764907  0.8075711466  0.9064065384  0.8691983122  0.8492746181  0.8217770930  0.7840050378  0.7317380353  0.4059910771  0.4047619048  9.0680100756  2.1561493154  2.2580189705  900           0.1817690333 
0.4137685187  0.8277808391  0.9248615871  0.8818565401  0.8604442162  0.8407806882  0.8132871537  0.7607052897  0.4219247929  0.4056122449  12.090680100  2.0404970419  2.2580189705  1200          0.1761997167 
0.4184440345  0.8494651992  0.9390983390  0.8976793249  0.8749518552  0.8597842835  0.8353274559  0.7909319899  0.4261737837  0.4107142857  15.113350125  1.9504847523  2.2580189705  1500          0.1785513417 
0.4257765245  0.8633127290  0.9443712101  0.9071729958  0.8813711645  0.8628659476  0.8501259446  0.8198992443  0.4314850223  0.4200680272  18.136020151  1.8583354056  2.2580189705  1800          0.1812842520 
0.4282210492  0.8682080165  0.9546533087  0.9029535865  0.8876620876  0.8767334361  0.8721662469  0.8249370277  0.4321223709  0.4243197279  21.158690176  1.7725363135  2.2580189705  2100          0.1816490134 
0.4343847958  0.8721814629  0.9567624572  0.9145569620  0.8974194377  0.8669748331  0.8863350126  0.8350125945  0.4359464627  0.4328231293  24.181360201  1.6887409361  2.2580189705  2400          0.1779778290 
0.4378912972  0.8891178337  0.9622989718  0.9229957806  0.9046090641  0.8828967643  0.8957808564  0.8614609572  0.4395581050  0.4362244898  27.204030226  1.6136906457  2.2580189705  2700          0.1810186982 
0.4398036140  0.8823725428  0.9678354864  0.9229957806  0.9083322634  0.8916281459  0.9093198992  0.8324937028  0.4425323986  0.4370748299  30.226700251  1.5590909330  2.2580189705  3000          0.1769413296 
0.4404401497  0.8963585017  0.9688900606  0.9324894515  0.9155218898  0.8900873138  0.9171914358  0.8664987406  0.4463564903  0.4345238095  33.249370277  1.5317659060  2.2580189705  3300          0.1778734692 
0.4383148413  0.8980003060  0.9744265753  0.9314345992  0.9179612274  0.8998459168  0.9203400504  0.8627204030  0.4446568940  0.4319727891  36.272040302  1.2936342901  5.3947548866  3600          0.1981001226 
0.4383153833  0.9018758903  0.9746902188  0.9388185654  0.9197586340  0.8977914741  0.9275818640  0.8690176322  0.4429572976  0.4336734694  39.294710327  1.0415732328  5.3947548866  3900          0.2136031493 
0.4348086109  0.9020300911  0.9749538624  0.9419831224  0.9245089228  0.9013867488  0.9335642317  0.8627204030  0.4401954536  0.4294217687  42.317380352  1.0226652640  5.3947548866  4200          0.2161625369 
0.4364036084  0.9023854342  0.9770630108  0.9345991561  0.9256643985  0.9085772984  0.9338790932  0.8639798489  0.4382834077  0.4345238095  45.340050377  1.0043563958  5.3947548866  4500          0.2149420826 
0.4353405477  0.9096281355  0.9804903770  0.9462025316  0.9306714598  0.9111453518  0.9379722922  0.8715365239  0.4387083068  0.4319727891  48.362720403  0.9855437577  5.3947548866  4800          0.2163774220 
0.4344907496  0.9083963206  0.9786448721  0.9493670886  0.9329824111  0.9080636877  0.9408060453  0.8677581864  0.4370087104  0.4319727891  50.377833753  0.9855725962  5.3947548866  5000          0.2176790488 
