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: 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: 1
	output_dir: sweep/ablation3/outputs/57d3eaf03c5ea2c2c6044b57fe60bc56
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1740336730
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	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: 0.7819049321936025
	lambda2: 0.9075316444347157
	last_k_epoch: 0.25491468830584113
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.907263233121133
	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    
0.0126765365  0.0158953229  0.0231719876  0.0144329897  0.0163230241  0.0183276060  0.0118243243  0.0135287486  0.0126219162  0.0149253731  0.0000000000  8.2200069427  2.0088801384  0             1.7115287781 
0.7214028075  0.7275807058  0.8496395469  0.7216494845  0.7666093929  0.6941580756  0.7314189189  0.7113866967  0.8485370052  0.7669345580  4.9433573635  5.8812068399  2.2550172806  300           0.3036076991 
0.7939447864  0.8155355917  0.9582904222  0.8226804124  0.8983390607  0.7800687285  0.7919481982  0.7959413754  0.9434882387  0.8438576349  9.8867147271  3.2667308736  2.2550172806  600           0.3067630760 
0.8080315197  0.8282999486  0.9809474768  0.8288659794  0.9349942726  0.7972508591  0.8020833333  0.8139797069  0.9621342513  0.8587830080  14.830072090  2.4587932460  2.2550172806  900           0.3146253737 
0.8170475114  0.8438108161  0.9897013388  0.8432989691  0.9521764032  0.8178694158  0.8077139640  0.8263810598  0.9750430293  0.8702640643  19.773429454  2.0913664997  2.2550172806  1200          0.3161386251 
0.8202863937  0.8396827210  0.9897013388  0.8412371134  0.9624856816  0.8132875143  0.8119369369  0.8286358512  0.9819277108  0.8645235362  24.716786817  1.8756441772  2.2550172806  1500          0.3147930439 
0.8235259106  0.8442698830  0.9938208033  0.8412371134  0.9702176403  0.8201603666  0.8150337838  0.8320180383  0.9845094664  0.8714121699  29.660144181  1.7434143174  2.2550172806  1800          0.3164750648 
0.8254972662  0.8529781261  0.9938208033  0.8536082474  0.9713631157  0.8304696449  0.8178490991  0.8331454340  0.9896729776  0.8748564868  34.603501544  1.6616660690  2.2550172806  2100          0.3110825062 
0.8262004602  0.8504580803  0.9948506694  0.8494845361  0.9750859107  0.8270332188  0.8203828829  0.8320180383  0.9911072863  0.8748564868  39.546858908  1.6354910926  2.2550172806  2400          0.3267778699 
0.8284546168  0.8509926354  0.9948506694  0.8453608247  0.9776632302  0.8327605956  0.8215090090  0.8354002255  0.9922547332  0.8748564868  44.490216271  1.5500480719  2.2550172806  2700          0.3285426927 
0.8308495392  0.8545817916  0.9963954686  0.8618556701  0.9799541810  0.8270332188  0.8229166667  0.8387824126  0.9934021801  0.8748564868  49.433573635  1.5274856790  2.2550172806  3000          0.3163565954 
0.8332444616  0.8542061037  0.9963954686  0.8515463918  0.9822451317  0.8281786942  0.8243243243  0.8421645998  0.9951233505  0.8828932262  54.376930999  1.4545243863  2.2550172806  3300          0.3183667660 
0.8350756862  0.8524426942  0.9963954686  0.8577319588  0.9828178694  0.8258877434  0.8257319820  0.8444193912  0.9951233505  0.8737083812  59.320288362  1.4360312164  2.2550172806  3600          0.3069373902 
0.8347941546  0.8513042328  0.9974253347  0.8474226804  0.9831042383  0.8235967927  0.8251689189  0.8444193912  0.9948364888  0.8828932262  64.263645726  1.3493432820  5.3966603279  3900          0.3109376947 
0.8353584873  0.8493047141  0.9943357364  0.8597938144  0.9802405498  0.8235967927  0.8240427928  0.8466741826  0.9951233505  0.8645235362  69.207003089  1.1598240217  5.3966603279  4200          0.2992840346 
0.8352177215  0.8529070216  0.9953656025  0.8453608247  0.9842497136  0.8316151203  0.8237612613  0.8466741826  0.9954102123  0.8817451206  74.150360453  1.0875110795  5.3966603279  4500          0.3067754817 
0.8359221852  0.8543562035  0.9948506694  0.8577319588  0.9859679267  0.8258877434  0.8240427928  0.8478015784  0.9959839357  0.8794489093  79.093717816  1.0323504897  5.3966603279  4800          0.2950613244 
0.8346540237  0.8551979723  0.9958805355  0.8659793814  0.9853951890  0.8178694158  0.8237612613  0.8455467869  0.9954102123  0.8817451206  82.389289392  1.0004745600  5.3966603279  5000          0.2901625514 
