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: 3
	output_dir: sweep/ablation3/outputs/783db9e19c91472151be499e24dd2027
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1369819541
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [0]
	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 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    
0.2061062040  0.1821222055  0.2068334350  0.2053789731  0.1839019190  0.1623931624  0.1863772455  0.1916167665  0.1902035623  0.1923566879  0.0000000000  7.8875064850  2.1691875458  0             1.6481864452 
0.8980146217  0.9594181496  0.8987187309  0.8973105134  0.9749466951  0.9594017094  0.9947604790  0.9940119760  0.9236641221  0.9248407643  7.1856287425  2.2583347742  2.4361939430  300           0.1511698508 
0.9212173916  0.9740216118  0.9255643685  0.9168704156  0.9925373134  0.9743589744  1.0000000000  0.9910179641  0.9688295165  0.9566878981  14.371257485  0.8963707983  2.4361939430  600           0.1712819982 
0.9138869036  0.9727341166  0.9206833435  0.9070904645  0.9962686567  0.9679487179  1.0000000000  0.9910179641  0.9767811705  0.9592356688  21.556886227  0.8106178876  2.4361939430  900           0.1735302925 
0.9166324801  0.9724582353  0.9261744966  0.9070904645  0.9968017058  0.9679487179  1.0000000000  0.9940119760  0.9751908397  0.9554140127  28.742514970  0.7382894527  2.4361939430  1200          0.1709727915 
0.9184651022  0.9742956242  0.9273947529  0.9095354523  0.9989339019  0.9700854701  1.0000000000  0.9910179641  0.9834605598  0.9617834395  35.928143712  0.7179807059  2.4361939430  1500          0.1700099953 
0.9175521476  0.9770057519  0.9231238560  0.9119804401  0.9946695096  0.9764957265  1.0000000000  0.9940119760  0.9837786260  0.9605095541  43.113772455  0.6676198002  2.4361939430  1800          0.1697506420 
0.9172470835  0.9752954972  0.9225137279  0.9119804401  0.9989339019  0.9743589744  1.0000000000  0.9910179641  0.9831424936  0.9605095541  50.299401197  0.6570259610  2.4361939430  2100          0.1705463155 
0.9199993730  0.9760040099  0.9206833435  0.9193154034  0.9973347548  0.9679487179  1.0000000000  0.9970059880  0.9866412214  0.9630573248  57.485029940  0.6392387179  2.4361939430  2400          0.1700256292 
0.9196965466  0.9781407621  0.9176327029  0.9217603912  0.9968017058  0.9743589744  1.0000000000  0.9970059880  0.9869592875  0.9630573248  64.670658682  0.6472961173  2.4361939430  2700          0.1699407705 
0.9221392967  0.9792776412  0.9200732154  0.9242053790  0.9994669510  0.9764957265  1.0000000000  0.9970059880  0.9875954198  0.9643312102  71.856287425  0.6134369784  2.4361939430  3000          0.1698002386 
0.9212218669  0.9765693825  0.9206833435  0.9217603912  0.9968017058  0.9743589744  1.0000000000  0.9910179641  0.9875954198  0.9643312102  79.041916167  0.3917484084  5.3991427422  3300          0.1986270102 
0.9206095011  0.9800016329  0.9219035998  0.9193154034  0.9978678038  0.9807692308  1.0000000000  1.0000000000  0.9869592875  0.9592356688  86.227544910  0.2923347237  5.3991427422  3600          0.2044329405 
0.9199971354  0.9797022697  0.9231238560  0.9168704156  0.9978678038  0.9764957265  0.9992514970  0.9970059880  0.9891857506  0.9656050955  93.413173652  0.2783351879  5.3991427422  3900          0.2053149414 
0.9199971354  0.9762953702  0.9231238560  0.9168704156  0.9978678038  0.9786324786  1.0000000000  0.9910179641  0.9875954198  0.9592356688  100.59880239  0.2701147654  5.3991427422  4200          0.2053075417 
0.9193870072  0.9779901460  0.9219035998  0.9168704156  0.9989339019  0.9700854701  0.9992514970  0.9970059880  0.9891857506  0.9668789809  107.78443113  0.2631403031  5.3991427422  4500          0.2043759608 
0.9187768791  0.9786925248  0.9206833435  0.9168704156  0.9984008529  0.9743589744  1.0000000000  0.9910179641  0.9904580153  0.9707006369  114.97005988  0.2574935940  5.3991427422  4800          0.2029727054 
0.9190819432  0.9802521634  0.9212934716  0.9168704156  0.9984008529  0.9722222222  1.0000000000  0.9940119760  0.9901399491  0.9745222930  119.76047904  0.2522087082  5.3991427422  5000          0.2051310670 
