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: [0]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: PACS
	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/71cf305f9d0278033b9e4dbeba9261b7
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1548653190
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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 normal transform
using augment 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    
0.1264061663  0.1361313140  0.1330079317  0.1198044010  0.1465884861  0.1346153846  0.1564371257  0.1616766467  0.1240458015  0.1121019108  0.0000000000  9.5738391876  2.0074062347  0             1.5671689510 
0.8726741658  0.9532875125  0.8700427090  0.8753056235  0.9765458422  0.9487179487  1.0000000000  0.9850299401  0.9487913486  0.9261146497  7.1856287425  3.0696598164  2.2544541359  300           0.1440605752 
0.9215246933  0.9650771946  0.9237339841  0.9193154034  0.9909381663  0.9615384615  1.0000000000  0.9910179641  0.9646946565  0.9426751592  14.371257485  1.2205630259  2.2544541359  600           0.1639171775 
0.9282428156  0.9636508242  0.9298352654  0.9266503667  0.9941364606  0.9529914530  0.9992514970  0.9940119760  0.9707379135  0.9439490446  21.556886227  1.0541605107  2.2544541359  900           0.1638500857 
0.9251854621  0.9699123335  0.9310555217  0.9193154034  0.9978678038  0.9722222222  1.0000000000  0.9910179641  0.9736005089  0.9464968153  28.742514970  0.9679329121  2.2544541359  1200          0.1639907400 
0.9236556665  0.9701962178  0.9328859060  0.9144254279  0.9973347548  0.9658119658  1.0000000000  0.9970059880  0.9796437659  0.9477707006  35.928143712  0.9402202183  2.2544541359  1500          0.1642377464 
0.9251832244  0.9738827367  0.9334960342  0.9168704156  0.9962686567  0.9722222222  1.0000000000  0.9940119760  0.9780534351  0.9554140127  43.113772455  0.8851136843  2.2544541359  1800          0.1632324354 
0.9221303462  0.9669127146  0.9298352654  0.9144254279  0.9989339019  0.9594017094  1.0000000000  0.9910179641  0.9825063613  0.9503184713  50.299401197  0.8704974530  2.2544541359  2100          0.1637167557 
0.9221303462  0.9718966006  0.9298352654  0.9144254279  0.9978678038  0.9700854701  1.0000000000  0.9940119760  0.9837786260  0.9515923567  57.485029940  0.8168557892  2.2544541359  2400          0.1640977597 
0.9236601418  0.9751584910  0.9280048810  0.9193154034  0.9978678038  0.9764957265  0.9992514970  0.9910179641  0.9860050891  0.9579617834  64.670658682  0.8159865743  2.2544541359  2700          0.1621381481 
0.9239652058  0.9740333528  0.9286150092  0.9193154034  0.9973347548  0.9764957265  1.0000000000  0.9940119760  0.9831424936  0.9515923567  71.856287425  0.7864975703  2.2544541359  3000          0.1617877571 
0.9212173916  0.9774322493  0.9255643685  0.9168704156  0.9984008529  0.9807692308  0.9992514970  0.9910179641  0.9866412214  0.9605095541  79.041916167  0.7711128289  2.2544541359  3300          0.1616475940 
0.9218275197  0.9714719722  0.9267846248  0.9168704156  0.9984008529  0.9700854701  1.0000000000  0.9940119760  0.9821882952  0.9503184713  86.227544910  0.7345187133  2.2544541359  3600          0.1617076437 
0.9218275197  0.9727594674  0.9267846248  0.9168704156  0.9989339019  0.9764957265  1.0000000000  0.9940119760  0.9872773537  0.9477707006  93.413173652  0.5890445212  5.3972430229  3900          0.1844332774 
0.9181600381  0.9708929897  0.9267846248  0.9095354523  0.9989339019  0.9572649573  1.0000000000  1.0000000000  0.9853689567  0.9554140127  100.59880239  0.4110288700  5.3972430229  4200          0.2011688431 
0.9175499100  0.9720453477  0.9255643685  0.9095354523  0.9989339019  0.9700854701  1.0000000000  0.9970059880  0.9875954198  0.9490445860  107.78443113  0.3775149598  5.3972430229  4500          0.2039985784 
0.9190774679  0.9740197429  0.9261744966  0.9119804401  1.0000000000  0.9700854701  1.0000000000  0.9940119760  0.9869592875  0.9579617834  114.97005988  0.3580560187  5.3972430229  4800          0.2061085908 
0.9184673398  0.9771662399  0.9249542404  0.9119804401  0.9994669510  0.9786324786  1.0000000000  1.0000000000  0.9885496183  0.9528662420  119.76047904  0.3449848121  5.3972430229  5000          0.2121259534 
