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: 4
	output_dir: sweep/ablation3/outputs/d3a226908cf4728f6ffab43efa65f8b7
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1309266490
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	trial_seed: 1
	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: 0.6171767606394463
	lambda2: 0.5293911814442921
	last_k_epoch: 0.3102645027326114
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.022572617872769
	weight_decay: 0.0001
	worst_case_p: 0.2
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    
0.0193298969  0.0158127047  0.0077239959  0.0144329897  0.0214776632  0.0171821306  0.0191441441  0.0157835400  0.0183591509  0.0172215844  0.0000000000  9.6467981339  1.7954735756  0             1.4716396332 
0.4829610536  0.7827056291  0.8486096807  0.7463917526  0.4825315006  0.4833906071  0.8620495495  0.8060879369  0.8582903041  0.7956371986  4.9433573635  5.7213044095  2.0968332291  300           0.3222033676 
0.5428121418  0.8632447336  0.9670442842  0.8185567010  0.5541237113  0.5315005727  0.9549549550  0.8940248027  0.9483648881  0.8771526980  9.8867147271  2.8612910744  2.0968332291  600           0.3135237312 
0.5541237111  0.8728629931  0.9876416066  0.8350515464  0.5607101947  0.5475372279  0.9743806306  0.9086809470  0.9678714859  0.8748564868  14.830072090  2.0252469031  2.0968332291  900           0.3124446670 
0.5592783502  0.8808652160  0.9876416066  0.8350515464  0.5664375716  0.5521191294  0.9811373874  0.9143179256  0.9764773379  0.8932261768  19.773429454  1.7043182965  2.0968332291  1200          0.3131849869 
0.5655784648  0.8921249431  0.9897013388  0.8701030928  0.5698739977  0.5612829324  0.9870495495  0.9210822999  0.9853700516  0.8851894374  24.716786817  1.5744973914  2.0968332291  1500          0.2995715610 
0.5687285221  0.8830399140  0.9927909372  0.8577319588  0.5727376861  0.5647193585  0.9878941441  0.9188275085  0.9890992542  0.8725602755  29.660144181  1.4763232315  2.0968332291  1800          0.3010414918 
0.5705899195  0.8910756659  0.9953656025  0.8680412371  0.5753150057  0.5658648339  0.9909909910  0.9177001127  0.9902467011  0.8874856487  34.603501544  1.4117294602  2.0968332291  2100          0.3113270291 
0.5737399768  0.8951015362  0.9953656025  0.8721649485  0.5758877434  0.5715922108  0.9929617117  0.9222096956  0.9925415950  0.8909299656  39.546858908  1.3688743130  2.0968332291  2400          0.3236293379 
0.5731672391  0.8938624929  0.9963954686  0.8639175258  0.5758877434  0.5704467354  0.9943693694  0.9255918828  0.9934021801  0.8920780712  44.490216271  1.3357158232  2.0968332291  2700          0.3094398729 
0.5733104235  0.8920340054  0.9974253347  0.8618556701  0.5784650630  0.5681557847  0.9949324324  0.9244644870  0.9934021801  0.8897818599  49.433573635  1.3195808140  2.0968332291  3000          0.2960685476 
0.5737399768  0.8970448410  0.9938208033  0.8701030928  0.5804696449  0.5670103093  0.9943693694  0.9301014656  0.9951233505  0.8909299656  54.376930999  1.3006502155  2.0968332291  3300          0.3094333386 
0.5725945014  0.8904053569  0.9958805355  0.8536082474  0.5827605956  0.5624284078  0.9946509009  0.9289740699  0.9959839357  0.8886337543  59.320288362  1.1571025493  5.4030575752  3600          0.3257373818 
0.5751718210  0.8896675664  0.9969104016  0.8536082474  0.5833333333  0.5670103093  0.9952139640  0.9244644870  0.9968445209  0.8909299656  64.263645726  0.8832582907  5.4030575752  3900          0.3072552562 
0.5763172964  0.8933622276  0.9958805355  0.8453608247  0.5833333333  0.5693012600  0.9940878378  0.9346110485  0.9956970740  0.9001148106  69.207003089  0.8235798005  5.4030575752  4200          0.3232238690 
0.5773195873  0.8945152616  0.9963954686  0.8659793814  0.5841924399  0.5704467354  0.9935247748  0.9312288613  0.9962707975  0.8863375431  74.150360453  0.7863584576  5.4030575752  4500          0.3186186266 
0.5756013743  0.8971872715  0.9963954686  0.8659793814  0.5830469645  0.5681557847  0.9960585586  0.9323562570  0.9948364888  0.8932261768  79.093717816  0.7531013344  5.4030575752  4800          0.3176194294 
0.5756013743  0.8897952028  0.9948506694  0.8597938144  0.5841924399  0.5670103093  0.9963400901  0.9278466742  0.9956970740  0.8817451206  82.389289392  0.7325716290  5.4030575752  5000          0.3139943027 
