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: 4
	output_dir: sweep/ablation3/outputs/98613c326e0c20810a0aa88812c442e7
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1525990358
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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 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    
0.0923394054  0.0399860183  0.0363828104  0.0358649789  0.0346642701  0.0374935799  0.0648614610  0.0465994962  0.0902910559  0.0943877551  0.0000000000  4.5470304489  1.7946186066  0             1.5674939156 
0.3400252228  0.6554574295  0.6841550224  0.7025316456  0.6617024008  0.6769388803  0.5935138539  0.5869017632  0.3475674527  0.3324829932  3.0226700252  2.6857344309  2.0947899818  300           0.1525104586 
0.3755162197  0.7960102840  0.8692327973  0.8597046414  0.8221851329  0.8217770930  0.7043450882  0.7065491184  0.3811344806  0.3698979592  6.0453400504  2.3271999009  2.0947899818  600           0.1725259868 
0.3815745544  0.8175445100  0.8892697074  0.8765822785  0.8341250481  0.8279404212  0.7462216625  0.7481108312  0.3821967283  0.3809523810  9.0680100756  2.2176862550  2.0947899818  900           0.1739747532 
0.3853997301  0.8236387506  0.9074611126  0.8966244726  0.8524842727  0.8412942989  0.7767632242  0.7329974811  0.3864457191  0.3843537415  12.090680100  2.1208631380  2.0947899818  1200          0.1732990615 
0.3958143644  0.8403144635  0.9224887951  0.8934599156  0.8667351393  0.8567026194  0.8044710327  0.7707808564  0.3928192054  0.3988095238  15.113350125  2.0574460884  2.0947899818  1500          0.1741144180 
0.3958143644  0.8550769987  0.9364619035  0.9008438819  0.8750802414  0.8633795583  0.8233627204  0.8010075567  0.3928192054  0.3988095238  18.136020151  1.9776725050  2.0947899818  1800          0.1741800197 
0.3977269523  0.8683343120  0.9412074875  0.9187763713  0.8854795224  0.8726245506  0.8435138539  0.8136020151  0.3949437009  0.4005102041  21.158690176  1.9044914726  2.0947899818  2100          0.1691620549 
0.3950705200  0.8740839251  0.9483258634  0.9251054852  0.8943381692  0.8772470467  0.8630352645  0.8198992443  0.3921818568  0.3979591837  24.181360201  1.8544600050  2.0947899818  2400          0.1722126532 
0.3949648372  0.8807969029  0.9528078038  0.9208860759  0.9005007061  0.8864920390  0.8743702771  0.8350125945  0.3902698109  0.3996598639  27.204030226  1.7786697300  2.0947899818  2700          0.1705919242 
0.3922013673  0.8853382652  0.9620353282  0.9293248945  0.9057645397  0.8941961993  0.8866498741  0.8324937028  0.3898449118  0.3945578231  30.226700251  1.7181465073  2.0947899818  3000          0.1761012276 
0.3911391196  0.8909500647  0.9659899815  0.9324894515  0.9096161253  0.8977914741  0.8910579345  0.8425692695  0.3877204164  0.3945578231  33.249370277  1.6657329381  2.0947899818  3300          0.1739427344 
0.3886948659  0.8970519107  0.9678354864  0.9367088608  0.9165489793  0.8967642527  0.9042821159  0.8576826196  0.3862332696  0.3911564626  36.272040302  1.3919532204  5.4009556770  3600          0.1978541795 
0.3891205779  0.9023796752  0.9665172687  0.9409282700  0.9195018616  0.9060092450  0.9105793451  0.8602015113  0.3845336733  0.3937074830  39.294710327  1.0969837403  5.4009556770  3900          0.2204710984 
0.3843382954  0.9034331096  0.9712628526  0.9388185654  0.9227115162  0.9049820236  0.9178211587  0.8664987406  0.3817718292  0.3869047619  42.317380352  1.0691203785  5.4009556770  4200          0.2230034479 
0.3861446584  0.9114806336  0.9704719220  0.9483122363  0.9236102195  0.9070364664  0.9156171285  0.8790931990  0.3836838751  0.3886054422  45.340050377  1.0513247818  5.4009556770  4500          0.2215901001 
0.3824246236  0.9132260591  0.9746902188  0.9451476793  0.9296443703  0.9116589625  0.9291561713  0.8828715365  0.3830465264  0.3818027211  48.362720403  1.0400842049  5.4009556770  4800          0.2189508526 
0.3822113611  0.9145039256  0.9765357237  0.9472573840  0.9328540249  0.9096045198  0.9253778338  0.8866498741  0.3851710219  0.3792517007  50.377833753  1.0313222662  5.4009556770  5000          0.2203185511 
