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: 4
	output_dir: sweep/ablation3/outputs/c5bbe9ea2fe2011fa7338a68175819c9
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 974705339
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	trial_seed: 2
	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: 0.5122476832929141
	lambda2: 0.9892716333303577
	last_k_epoch: 0.2899069879248226
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.19589595208549
	weight_decay: 0.0001
	worst_case_p: 0.3
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    
0.1532517706  0.1566543318  0.1751067724  0.1466992665  0.1183368870  0.1047008547  0.1923652695  0.2185628743  0.1447201018  0.1617834395  0.0000000000  9.0430812836  2.1691875458  0             1.7375667095 
0.7395023983  0.9678320409  0.9786455156  0.9633251834  0.9754797441  0.9401709402  0.9985029940  1.0000000000  0.7312340967  0.7477707006  7.1856287425  2.6500453784  2.4373230934  300           0.1520818512 
0.7716473392  0.9738537988  0.9920683344  0.9608801956  0.9893390192  0.9636752137  1.0000000000  0.9970059880  0.7636768448  0.7796178344  14.371257485  0.8865000399  2.4373230934  600           0.1746504021 
0.7776914066  0.9756667987  0.9945088469  0.9633251834  0.9893390192  0.9636752137  0.9992514970  1.0000000000  0.7744910941  0.7808917197  21.556886227  0.7550240203  2.4373230934  900           0.1756458282 
0.7838985588  0.9816730400  0.9932885906  0.9706601467  0.9957356077  0.9743589744  0.9992514970  1.0000000000  0.7792620865  0.7885350318  28.742514970  0.6994540086  2.4373230934  1200          0.1765353672 
0.7888310153  0.9724292974  0.9938987187  0.9608801956  0.9952025586  0.9594017094  0.9992514970  0.9970059880  0.7853053435  0.7923566879  35.928143712  0.6618380791  2.4373230934  1500          0.1775879622 
0.7905795688  0.9783103111  0.9981696156  0.9584352078  0.9957356077  0.9764957265  1.0000000000  1.0000000000  0.7900763359  0.7910828025  43.113772455  0.6293435916  2.4373230934  1800          0.1761815174 
0.7916936107  0.9840152826  0.9981696156  0.9755501222  0.9968017058  0.9764957265  1.0000000000  1.0000000000  0.7910305344  0.7923566879  50.299401197  0.6106646153  2.4373230934  2100          0.1765688396 
0.7961513991  0.9791477894  0.9987797437  0.9682151589  0.9984008529  0.9722222222  1.0000000000  0.9970059880  0.7923027990  0.8000000000  57.485029940  0.5855194903  2.4373230934  2400          0.1769472488 
0.7985368953  0.9769885549  0.9975594875  0.9608801956  0.9984008529  0.9700854701  0.9985029940  1.0000000000  0.7970737913  0.8000000000  64.670658682  0.5990020469  2.4373230934  2700          0.1761862755 
0.8023561202  0.9779062960  0.9981696156  0.9657701711  0.9989339019  0.9679487179  1.0000000000  1.0000000000  0.8008905852  0.8038216561  71.856287425  0.5690692795  2.4373230934  3000          0.1768317962 
0.8041071048  0.9838097922  0.9975594875  0.9706601467  0.9973347548  0.9807692308  1.0000000000  1.0000000000  0.8018447837  0.8063694268  79.041916167  0.5604010490  2.4373230934  3300          0.1823303556 
0.8061761556  0.9771940453  0.9975594875  0.9657701711  0.9984008529  0.9658119658  1.0000000000  1.0000000000  0.8034351145  0.8089171975  86.227544910  0.5331340219  5.3971133232  3600          0.1859509341 
0.8058580894  0.9791253070  0.9993898719  0.9608801956  1.0000000000  0.9764957265  1.0000000000  1.0000000000  0.8027989822  0.8089171975  93.413173652  0.3495687848  5.3971133232  3900          0.2139036036 
0.8055392129  0.9741550686  0.9981696156  0.9511002445  0.9994669510  0.9743589744  1.0000000000  0.9970059880  0.8034351145  0.8076433121  100.59880239  0.3169228606  5.3971133232  4200          0.2138101157 
0.8071303540  0.9775177975  0.9987797437  0.9633251834  0.9994669510  0.9722222222  0.9992514970  0.9970059880  0.8053435115  0.8089171975  107.78443113  0.2980056855  5.3971133232  4500          0.2155116232 
0.8090395614  0.9838097922  0.9975594875  0.9706601467  0.9994669510  0.9807692308  1.0000000000  1.0000000000  0.8078880407  0.8101910828  114.97005988  0.2827855606  5.3971133232  4800          0.2153969081 
0.8087206848  0.9774150523  0.9981696156  0.9608801956  0.9994669510  0.9743589744  1.0000000000  0.9970059880  0.8085241730  0.8089171975  119.76047904  0.2735610002  5.3971133232  5000          0.2143653703 
