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: [1]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: OfficeHome
	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/5ddc665b00c00bbd17d96fe9e43d8820
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1117209205
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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: 0.6109302038716249
	lambda2: 0.5117744391412766
	last_k_epoch: 0.31317984427858747
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.002688876693512
	weight_decay: 1e-06
	worst_case_p: 0.25
using augment transform
using normal 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    
0.0085910653  0.0256047415  0.0298661174  0.0391752577  0.0114547537  0.0057273769  0.0098536036  0.0135287486  0.0286861733  0.0241102181  0.0000000000  7.8868827820  2.0088801384  0             1.6366033554 
0.4876861395  0.8111459442  0.8934088568  0.7463917526  0.4908361970  0.4845360825  0.9087837838  0.8489289741  0.8975903614  0.8381171068  4.9433573635  4.6067128309  2.2550172806  300           0.3075702580 
0.5459621990  0.8614598481  0.9763130793  0.8144329897  0.5432416953  0.5486827033  0.9662162162  0.8985343856  0.9586919105  0.8714121699  9.8867147271  2.2154062653  2.2550172806  600           0.3113887970 
0.5577033216  0.8653363847  0.9897013388  0.8226804124  0.5529782360  0.5624284078  0.9802927928  0.9019165727  0.9770510614  0.8714121699  14.830072090  1.6200191287  2.2550172806  900           0.3105266341 
0.5622852231  0.8704056164  0.9922760041  0.8185567010  0.5587056128  0.5658648339  0.9876126126  0.9120631342  0.9859437751  0.8805970149  19.773429454  1.3714999394  2.2550172806  1200          0.3130357997 
0.5685853376  0.8723250416  0.9953656025  0.8288659794  0.5667239404  0.5704467354  0.9901463964  0.9098083427  0.9919678715  0.8783008037  24.716786817  1.2689875221  2.2550172806  1500          0.3125069404 
0.5735967924  0.8770105840  0.9948506694  0.8350515464  0.5687285223  0.5784650630  0.9926801802  0.9188275085  0.9931153184  0.8771526980  29.660144181  1.1960043208  2.2550172806  1800          0.3122165600 
0.5768900341  0.8732121659  0.9969104016  0.8247422680  0.5718785796  0.5819014891  0.9909909910  0.9154453213  0.9936890419  0.8794489093  34.603501544  1.1441472725  2.2550172806  2100          0.3086092170 
0.5808991979  0.8718444988  0.9943357364  0.8206185567  0.5764604811  0.5853379152  0.9949324324  0.9143179256  0.9934021801  0.8805970149  39.546858908  1.0855340703  2.2550172806  2400          0.2971431343 
0.5800400913  0.8788230828  0.9958805355  0.8391752577  0.5770332188  0.5830469645  0.9960585586  0.9098083427  0.9956970740  0.8874856487  44.490216271  1.0606794657  2.2550172806  2700          0.3063619177 
0.5839060707  0.8753107203  0.9953656025  0.8288659794  0.5801832761  0.5876288660  0.9960585586  0.9222096956  0.9954102123  0.8748564868  49.433573635  1.0385154365  2.2550172806  3000          0.3143289407 
0.5841924396  0.8770105840  0.9953656025  0.8350515464  0.5807560137  0.5876288660  0.9974662162  0.9188275085  0.9962707975  0.8771526980  54.376930999  1.0084335013  2.2550172806  3300          0.3051030191 
0.5863402059  0.8808445061  0.9948506694  0.8350515464  0.5827605956  0.5899198167  0.9960585586  0.9177001127  0.9971313827  0.8897818599  59.320288362  0.9322235936  5.3961720467  3600          0.3109088095 
0.5869129436  0.8833592914  0.9953656025  0.8494845361  0.5827605956  0.5910652921  0.9954954955  0.9177001127  0.9968445209  0.8828932262  64.263645726  0.7932206368  5.3961720467  3900          0.3053884482 
0.5889175255  0.8827165956  0.9953656025  0.8350515464  0.5844788087  0.5933562428  0.9969031532  0.9244644870  0.9959839357  0.8886337543  69.207003089  0.7432059534  5.3961720467  4200          0.3010089620 
0.5861970215  0.8843166434  0.9948506694  0.8536082474  0.5824742268  0.5899198167  0.9971846847  0.9233370913  0.9968445209  0.8760045924  74.150360453  0.7097422415  5.3961720467  4500          0.3115512760 
0.5887743411  0.8864783150  0.9958805355  0.8474226804  0.5853379152  0.5922107675  0.9960585586  0.9210822999  0.9965576592  0.8909299656  79.093717816  0.6781473384  5.3961720467  4800          0.3223023319 
0.5899198164  0.8898445133  0.9963954686  0.8494845361  0.5864833906  0.5933562428  0.9966216216  0.9210822999  0.9965576592  0.8989667049  82.389289392  0.6578247070  5.3961720467  5000          0.3195980918 
