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: 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/b0acf2ec40e36d1690f1936e7f6b3889
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1259611048
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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: 0.6880433961757358
	lambda2: 0.9840350138898164
	last_k_epoch: 0.33648211095401626
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 3.599417945900826
	weight_decay: 0.0001
	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    
0.1608804962  0.1745249183  0.2190359976  0.2029339853  0.2004264392  0.1709401709  0.1444610778  0.1497005988  0.1676208651  0.1541401274  0.0000000000  9.4720993042  2.0074062347  0             1.4652004242 
0.7921739514  0.9569963053  0.9810860281  0.9462102689  0.9765458422  0.9337606838  0.9992514970  0.9910179641  0.7868956743  0.7974522293  7.1856287425  3.1006489799  2.2544541359  300           0.1502237105 
0.7864479502  0.9747292760  0.9951189750  0.9682151589  0.9920042644  0.9679487179  1.0000000000  0.9880239521  0.7767175573  0.7961783439  14.371257485  1.0543592538  2.2544541359  600           0.1739478326 
0.7924928279  0.9739790263  0.9938987187  0.9706601467  0.9930703625  0.9572649573  0.9992514970  0.9940119760  0.7862595420  0.7987261146  21.556886227  0.9421532025  2.2544541359  900           0.1717924960 
0.8082516892  0.9712482853  0.9938987187  0.9633251834  0.9962686567  0.9594017094  1.0000000000  0.9910179641  0.7948473282  0.8216560510  28.742514970  0.8586483818  2.2544541359  1200          0.1720807568 
0.8104797730  0.9713665471  0.9957291031  0.9559902200  0.9946695096  0.9700854701  1.0000000000  0.9880239521  0.7967557252  0.8242038217  35.928143712  0.8262990900  2.2544541359  1500          0.1712344273 
0.8138227091  0.9742000334  0.9969493594  0.9657701711  0.9962686567  0.9658119658  1.0000000000  0.9910179641  0.7983460560  0.8292993631  43.113772455  0.7872971114  2.2544541359  1800          0.1733066551 
0.8160483619  0.9760355156  0.9987797437  0.9755501222  0.9962686567  0.9615384615  1.0000000000  0.9910179641  0.8040712468  0.8280254777  50.299401197  0.7397616114  2.2544541359  2100          0.1712306746 
0.8193904876  0.9756245348  0.9987797437  0.9657701711  0.9989339019  0.9700854701  1.0000000000  0.9910179641  0.8069338422  0.8318471338  57.485029940  0.7115632755  2.2544541359  2400          0.1727164570 
0.8220964810  0.9764620131  0.9981696156  0.9755501222  0.9984008529  0.9658119658  0.9992514970  0.9880239521  0.8085241730  0.8356687898  64.670658682  0.7549818939  2.2544541359  2700          0.1728408464 
0.8259157060  0.9767252840  0.9987797437  0.9682151589  0.9978678038  0.9679487179  1.0000000000  0.9940119760  0.8123409669  0.8394904459  71.856287425  0.6932714853  2.2544541359  3000          0.1801541376 
0.8295750875  0.9749925469  0.9975594875  0.9608801956  0.9989339019  0.9700854701  1.0000000000  0.9940119760  0.8171119593  0.8420382166  79.041916167  0.6698439429  2.2544541359  3300          0.1787586697 
0.8295734668  0.9748095389  0.9993898719  0.9633251834  0.9989339019  0.9700854701  1.0000000000  0.9910179641  0.8196564885  0.8394904459  86.227544910  0.5570511641  5.3972430229  3600          0.2134738374 
0.8284578042  0.9804117651  0.9987797437  0.9779951100  0.9994669510  0.9722222222  1.0000000000  0.9910179641  0.8212468193  0.8356687898  93.413173652  0.4679188860  5.3972430229  3900          0.2138205806 
0.8303678218  0.9755442719  0.9987797437  0.9706601467  0.9984008529  0.9679487179  1.0000000000  0.9880239521  0.8225190840  0.8382165605  100.59880239  0.4283514825  5.3972430229  4200          0.2116842906 
0.8310039541  0.9736060444  1.0000000000  0.9584352078  0.9994669510  0.9743589744  1.0000000000  0.9880239521  0.8237913486  0.8382165605  107.78443113  0.3924972206  5.3972430229  4500          0.2100109633 
0.8306850776  0.9732020294  1.0000000000  0.9657701711  0.9989339019  0.9658119658  1.0000000000  0.9880239521  0.8244274809  0.8369426752  114.97005988  0.3738296328  5.3972430229  4800          0.2121478105 
0.8303662011  0.9741802518  0.9993898719  0.9755501222  0.9984008529  0.9679487179  1.0000000000  0.9790419162  0.8250636132  0.8356687898  119.76047904  0.3613427182  5.3972430229  5000          0.2132707000 
