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: VLCS
	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/c06b63fbb9f19e4384b332a630cdf0b1
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 822782590
	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    
0.1673772402  0.1073901021  0.0477031802  0.0671378092  0.1096470588  0.1224105461  0.1344249810  0.1326219512  0.1629026287  0.1718518519  0.0000000000  4.9818134308  2.0073552132  0             1.5798816681 
0.8087402467  0.8523360584  0.9991166078  1.0000000000  0.7665882353  0.7551789077  0.8750952018  0.8018292683  0.8026656794  0.8148148148  8.4805653710  1.8639663720  2.2565736771  300           0.6471697434 
0.8324384654  0.8616020162  1.0000000000  1.0000000000  0.7920000000  0.7570621469  0.9131759330  0.8277439024  0.8322843391  0.8325925926  16.961130742  1.3904646715  2.2565736771  600           0.6388526217 
0.8298476555  0.8602269071  1.0000000000  1.0000000000  0.8127058824  0.7514124294  0.9417364813  0.8292682927  0.8226582747  0.8370370370  25.441696113  1.2857037854  2.2565736771  900           0.6406525644 
0.8276248847  0.8617216325  1.0000000000  1.0000000000  0.8310588235  0.7589453861  0.9615384615  0.8262195122  0.8256201407  0.8296296296  33.922261484  1.1218333403  2.2565736771  1200          0.6238355565 
0.8259580124  0.8587025168  1.0000000000  1.0000000000  0.8541176471  0.7514124294  0.9680121858  0.8246951220  0.8267308404  0.8251851852  42.402826855  1.0255408412  2.2565736771  1500          0.6231438502 
0.8272546515  0.8644718506  1.0000000000  1.0000000000  0.8710588235  0.7702448211  0.9737242955  0.8231707317  0.8248796742  0.8296296296  50.883392226  0.9721618251  2.2565736771  1800          0.6416366593 
0.8228107556  0.8600776259  1.0000000000  1.0000000000  0.8804705882  0.7570621469  0.9840060929  0.8231707317  0.8219178082  0.8237037037  59.363957597  0.9602316527  2.2565736771  2100          0.6410905957 
0.8213295483  0.8621101462  1.0000000000  1.0000000000  0.9082352941  0.7570621469  0.9912414318  0.8292682927  0.8204368752  0.8222222222  67.844522968  0.9254758592  2.2565736771  2400          0.6234556039 
0.8192927170  0.8604661397  1.0000000000  1.0000000000  0.9176470588  0.7551789077  0.9897182026  0.8262195122  0.8193261755  0.8192592593  76.325088339  0.9241319356  2.2565736771  2700          0.6344388914 
0.8216992331  0.8558929690  1.0000000000  1.0000000000  0.9218823529  0.7551789077  0.9942878903  0.8125000000  0.8241392077  0.8192592593  84.805653710  0.9178719294  2.2565736771  3000          0.6414806509 
0.8222545829  0.8665043710  1.0000000000  1.0000000000  0.9345882353  0.7702448211  0.9954303123  0.8292682927  0.8252499074  0.8192592593  93.286219081  0.9079430991  2.2565736771  3300          0.6230355628 
0.8239211810  0.8621101462  1.0000000000  1.0000000000  0.9468235294  0.7570621469  0.9950495050  0.8292682927  0.8256201407  0.8222222222  101.76678445  0.5253739503  5.3972864151  3600          0.6387897499 
0.8241065719  0.8653684945  1.0000000000  1.0000000000  0.9472941176  0.7683615819  0.9950495050  0.8277439024  0.8245094409  0.8237037037  110.24734982  0.4539976420  5.3972864151  3900          0.6317214473 
0.8261436775  0.8667436036  1.0000000000  1.0000000000  0.9543529412  0.7740112994  0.9942878903  0.8262195122  0.8241392077  0.8281481481  118.72791519  0.4395562774  5.3972864151  4200          0.6339116589 
0.8289212496  0.8686565076  1.0000000000  1.0000000000  0.9557647059  0.7721280603  0.9950495050  0.8338414634  0.8252499074  0.8325925926  127.20848056  0.4282543593  5.3972864151  4500          0.6428499730 
0.8281805089  0.8637541528  1.0000000000  1.0000000000  0.9576470588  0.7589453861  0.9973343488  0.8323170732  0.8252499074  0.8311111111  135.68904593  0.4211801991  5.3972864151  4800          0.6475810107 
0.8292914828  0.8634852553  1.0000000000  1.0000000000  0.9600000000  0.7627118644  0.9946686976  0.8277439024  0.8259903739  0.8325925926  141.34275618  0.4189892887  5.3972864151  5000          0.6443279910 
