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/a1ef22841086f4a79003db6f03f3f384
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1025946942
	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: 0.8194577311903198
	lambda2: 0.5954971958468116
	last_k_epoch: 0.2502561813215683
	lr: 3e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.3092434210820203
	weight_decay: 1e-06
	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    
0.1432205312  0.1247930653  0.1177547285  0.1075794621  0.0868869936  0.1111111111  0.1714071856  0.1556886228  0.1437659033  0.1426751592  0.0000000000  9.2155284882  2.0074062347  0             1.4123187065 
0.7213580408  0.9635093069  0.9755948749  0.9486552567  0.9733475480  0.9508547009  0.9955089820  0.9910179641  0.7178753181  0.7248407643  7.1856287425  2.7317136141  2.2566514015  300           0.1491530816 
0.7453866222  0.9672380519  0.9884075656  0.9559902200  0.9909381663  0.9487179487  1.0000000000  0.9970059880  0.7430025445  0.7477707006  14.371257485  0.9468360656  2.2566514015  600           0.1720328307 
0.7644811263  0.9747715399  0.9938987187  0.9657701711  0.9957356077  0.9615384615  1.0000000000  0.9970059880  0.7646310433  0.7643312102  21.556886227  0.8177064743  2.2566514015  900           0.1694553574 
0.7762560571  0.9734428179  0.9926784625  0.9511002445  0.9946695096  0.9722222222  1.0000000000  0.9970059880  0.7779898219  0.7745222930  28.742514970  0.7391829507  2.2566514015  1200          0.1691622957 
0.7740271629  0.9773192729  0.9945088469  0.9755501222  0.9925373134  0.9594017094  0.9992514970  0.9970059880  0.7773536896  0.7707006369  35.928143712  0.7186581618  2.2566514015  1500          0.1682170947 
0.7756199247  0.9787592909  0.9975594875  0.9657701711  0.9946695096  0.9764957265  1.0000000000  0.9940119760  0.7767175573  0.7745222930  43.113772455  0.6859938637  2.2566514015  1800          0.1703833040 
0.7808704474  0.9804695456  0.9969493594  0.9657701711  0.9962686567  0.9786324786  0.9992514970  0.9970059880  0.7833969466  0.7783439490  50.299401197  0.6676110693  2.2566514015  2100          0.1761025961 
0.7845314497  0.9804920280  0.9963392312  0.9731051345  0.9962686567  0.9743589744  1.0000000000  0.9940119760  0.7856234097  0.7834394904  57.485029940  0.6648088003  2.2566514015  2400          0.1748742231 
0.7846904827  0.9737510536  0.9957291031  0.9584352078  0.9978678038  0.9658119658  0.9992514970  0.9970059880  0.7859414758  0.7834394904  64.670658682  0.6449937984  2.2566514015  2700          0.1712673887 
0.7880334188  0.9765197936  0.9987797437  0.9633251834  0.9973347548  0.9722222222  1.0000000000  0.9940119760  0.7875318066  0.7885350318  71.856287425  0.6344661396  2.2566514015  3000          0.1697009118 
0.7901024696  0.9804695456  0.9987797437  0.9657701711  0.9968017058  0.9786324786  1.0000000000  0.9970059880  0.7891221374  0.7910828025  79.041916167  0.6227216634  2.2566514015  3300          0.1713915650 
0.7888285842  0.9803892828  0.9987797437  0.9706601467  0.9962686567  0.9764957265  1.0000000000  0.9940119760  0.7891221374  0.7885350318  86.227544910  0.6280749577  2.2566514015  3600          0.1748600849 
0.7920124872  0.9809607893  0.9981696156  0.9706601467  0.9978678038  0.9722222222  1.0000000000  1.0000000000  0.7903944020  0.7936305732  93.413173652  0.4903929796  5.3973727226  3900          0.1927172335 
0.7936036284  0.9774150523  0.9969493594  0.9608801956  0.9989339019  0.9743589744  1.0000000000  0.9970059880  0.7923027990  0.7949044586  100.59880239  0.3312472600  5.3973727226  4200          0.2087298457 
0.7940815380  0.9811817963  0.9957291031  0.9657701711  0.9994669510  0.9807692308  0.9992514970  0.9970059880  0.7919847328  0.7961783439  107.78443113  0.3066158349  5.3973727226  4500          0.2074530657 
0.7961497784  0.9774150523  0.9981696156  0.9608801956  0.9968017058  0.9743589744  1.0000000000  0.9970059880  0.7948473282  0.7974522293  114.97005988  0.2893673725  5.3973727226  4800          0.2056984409 
0.7979007630  0.9805722908  0.9987797437  0.9682151589  0.9978678038  0.9764957265  1.0000000000  0.9970059880  0.7958015267  0.8000000000  119.76047904  0.2843031882  5.3973727226  5000          0.2094728601 
