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: [1]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: OfficeHome
	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/4254cd14069b5ef684b2b91404fb4db8
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 625331468
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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: 0.7010166027828918
	lambda2: 0.6269010951324223
	last_k_epoch: 0.38851977780027735
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.131347198605345
	weight_decay: 1e-06
	worst_case_p: 0.3
using augment transform
using normal transform
using augment 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    
0.0194730813  0.0102698334  0.0175077240  0.0103092784  0.0171821306  0.0217640321  0.0129504505  0.0090191657  0.0086058520  0.0114810563  0.0000000000  10.797281265  2.1706647873  0             1.4228377342 
0.4955612827  0.8138207002  0.8887744593  0.7690721649  0.5111683849  0.4799541810  0.8913288288  0.8342728298  0.8915662651  0.8381171068  4.9433573635  5.3766297340  2.4395728111  300           0.2906959534 
0.5469644900  0.8574031949  0.9701338826  0.8226804124  0.5612829324  0.5326460481  0.9656531532  0.8850056370  0.9578313253  0.8645235362  9.8867147271  2.4478207155  2.4395728111  600           0.3073433860 
0.5552691864  0.8723021495  0.9819773429  0.8309278351  0.5710194731  0.5395189003  0.9735360360  0.9007891770  0.9690189329  0.8851894374  14.830072090  1.8998370671  2.4395728111  900           0.3060480881 
0.5558419241  0.8707506321  0.9902162719  0.8309278351  0.5698739977  0.5418098511  0.9825450450  0.9041713641  0.9770510614  0.8771526980  19.773429454  1.6968464271  2.4395728111  1200          0.3070726864 
0.5611397477  0.8767602396  0.9927909372  0.8432989691  0.5724513173  0.5498281787  0.9850788288  0.9086809470  0.9819277108  0.8783008037  24.716786817  1.6014852528  2.4395728111  1500          0.2980434910 
0.5622852231  0.8732604890  0.9948506694  0.8247422680  0.5758877434  0.5486827033  0.9884572072  0.9075535513  0.9839357430  0.8874856487  29.660144181  1.5133035596  2.4395728111  1800          0.3139669379 
0.5665807557  0.8777759878  0.9948506694  0.8350515464  0.5787514318  0.5544100802  0.9915540541  0.9188275085  0.9896729776  0.8794489093  34.603501544  1.4475573353  2.4395728111  2100          0.3151700020 
0.5652920959  0.8763578153  0.9943357364  0.8329896907  0.5784650630  0.5521191294  0.9918355856  0.9131905299  0.9865174986  0.8828932262  39.546858908  1.3987521823  2.4395728111  2400          0.3007675823 
0.5655784648  0.8831397299  0.9958805355  0.8453608247  0.5801832761  0.5509736541  0.9921171171  0.9165727170  0.9902467011  0.8874856487  44.490216271  1.3570241002  2.4395728111  2700          0.2969191933 
0.5638602517  0.8828994584  0.9948506694  0.8412371134  0.5790378007  0.5486827033  0.9946509009  0.9188275085  0.9931153184  0.8886337543  49.433573635  1.3232005537  2.4395728111  3000          0.3092156959 
0.5642898050  0.8788092761  0.9948506694  0.8391752577  0.5798969072  0.5486827033  0.9929617117  0.9120631342  0.9925415950  0.8851894374  54.376930999  1.1260131313  5.3998112679  3300          0.2946975970 
0.5672966778  0.8839763488  0.9969104016  0.8432989691  0.5824742268  0.5521191294  0.9932432432  0.9177001127  0.9936890419  0.8909299656  59.320288362  0.9671240121  5.3998112679  3600          0.2995603331 
0.5688717065  0.8798516500  0.9963954686  0.8412371134  0.5833333333  0.5544100802  0.9923986486  0.9165727170  0.9939759036  0.8817451206  64.263645726  0.9099349596  5.3998112679  3900          0.2907907120 
0.5698739974  0.8826086817  0.9969104016  0.8391752577  0.5853379152  0.5544100802  0.9952139640  0.9165727170  0.9939759036  0.8920780712  69.207003089  0.8710609615  5.3998112679  4200          0.3010561331 
0.5693012597  0.8801572208  0.9963954686  0.8329896907  0.5864833906  0.5521191294  0.9949324324  0.9177001127  0.9959839357  0.8897818599  74.150360453  0.8465130925  5.3998112679  4500          0.2995224484 
0.5703035507  0.8850325293  0.9958805355  0.8453608247  0.5861970218  0.5544100802  0.9932432432  0.9199549042  0.9936890419  0.8897818599  79.093717816  0.8180219930  5.3998112679  4800          0.2855669777 
0.5715922105  0.8788092761  0.9958805355  0.8391752577  0.5864833906  0.5567010309  0.9963400901  0.9120631342  0.9956970740  0.8851894374  82.389289392  0.8043970186  5.3998112679  5000          0.2902017903 
