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: 2
	output_dir: sweep/ablation3/outputs/e8abaa4cedaa4387a749692fcf397fb6
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 388611366
	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: 0.7419102898692578
	lambda2: 0.5215383105176172
	last_k_epoch: 0.23762453204831346
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.9748462276330736
	weight_decay: 1e-06
	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    
0.0873626440  0.1300502145  0.1067724222  0.1246943765  0.1481876333  0.1816239316  0.0688622754  0.0838323353  0.0906488550  0.0840764331  0.0000000000  7.9792757034  2.1691875458  0             1.4442751408 
0.7132433020  0.9592893181  0.9707138499  0.9364303178  0.9776119403  0.9594017094  0.9970059880  0.9820359281  0.7080152672  0.7184713376  7.1856287425  2.5284558680  2.4361939430  300           0.1519480141 
0.7283619792  0.9690087879  0.9902379500  0.9608801956  0.9866737740  0.9551282051  0.9985029940  0.9910179641  0.7216921120  0.7350318471  14.371257485  0.8524172185  2.4361939430  600           0.1739875158 
0.7417304821  0.9669678152  0.9951189750  0.9462102689  0.9920042644  0.9636752137  1.0000000000  0.9910179641  0.7331424936  0.7503184713  21.556886227  0.7268492177  2.4361939430  900           0.1743883769 
0.7525544558  0.9689863056  0.9951189750  0.9535452323  0.9925373134  0.9594017094  0.9992514970  0.9940119760  0.7395038168  0.7656050955  28.742514970  0.6626218128  2.4361939430  1200          0.1740682149 
0.7613093787  0.9696760739  0.9938987187  0.9462102689  0.9930703625  0.9658119658  1.0000000000  0.9970059880  0.7442748092  0.7783439490  35.928143712  0.6323651137  2.4361939430  1500          0.1729861355 
0.7735662708  0.9714692923  0.9963392312  0.9584352078  0.9968017058  0.9679487179  1.0000000000  0.9880239521  0.7509541985  0.7961783439  43.113772455  0.6066595237  2.4361939430  1800          0.1742471727 
0.7756337008  0.9701475361  0.9963392312  0.9608801956  0.9968017058  0.9615384615  0.9992514970  0.9880239521  0.7550890585  0.7961783439  50.299401197  0.5986862960  2.4361939430  2100          0.1742750065 
0.7797726127  0.9669902976  0.9975594875  0.9535452323  0.9984008529  0.9594017094  1.0000000000  0.9880239521  0.7569974555  0.8025477707  57.485029940  0.5571393589  2.4361939430  2400          0.1735741806 
0.7786577604  0.9783327935  0.9981696156  0.9657701711  0.9978678038  0.9722222222  1.0000000000  0.9970059880  0.7573155216  0.8000000000  64.670658682  0.5770419316  2.4361939430  2700          0.1737341928 
0.7792922720  0.9745660495  1.0000000000  0.9608801956  0.9973347548  0.9658119658  1.0000000000  0.9970059880  0.7611323155  0.7974522293  71.856287425  0.5466171837  2.4361939430  3000          0.1746804245 
0.7819966447  0.9734653003  0.9987797437  0.9584352078  0.9978678038  0.9679487179  1.0000000000  0.9940119760  0.7652671756  0.7987261146  79.041916167  0.5526337919  2.4361939430  3300          0.1746089689 
0.7842247285  0.9751980373  0.9981696156  0.9657701711  0.9994669510  0.9658119658  1.0000000000  0.9940119760  0.7671755725  0.8012738854  86.227544910  0.5342371252  2.4361939430  3600          0.1725408371 
0.7840656955  0.9715720375  0.9981696156  0.9608801956  0.9984008529  0.9658119658  1.0000000000  0.9880239521  0.7668575064  0.8012738854  93.413173652  0.4907169717  5.3991427422  3900          0.1838371070 
0.7824737440  0.9733850374  0.9987797437  0.9633251834  0.9989339019  0.9658119658  1.0000000000  0.9910179641  0.7662213740  0.7987261146  100.59880239  0.3369649862  5.3991427422  4200          0.2075437172 
0.7856560263  0.9733625551  0.9969493594  0.9559902200  0.9994669510  0.9700854701  1.0000000000  0.9940119760  0.7700381679  0.8012738854  107.78443113  0.3127402254  5.3991427422  4500          0.2065041494 
0.7872479778  0.9759102881  0.9987797437  0.9657701711  0.9978678038  0.9679487179  1.0000000000  0.9940119760  0.7706743003  0.8038216561  114.97005988  0.2915323068  5.3991427422  4800          0.2086516023 
0.7886808962  0.9767028016  0.9981696156  0.9608801956  0.9989339019  0.9722222222  1.0000000000  0.9970059880  0.7709923664  0.8063694268  119.76047904  0.2929369902  5.3991427422  5000          0.2116397727 
