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: 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: 2
	output_dir: sweep/ablation3/outputs/f5436f963e20f6022e825780f8e681ab
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 552549837
	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    
0.0111909010  0.0152308191  0.0133882595  0.0206185567  0.0117411226  0.0171821306  0.0087274775  0.0078917700  0.0109007458  0.0114810563  0.0000000000  8.6666984558  2.0088801384  0             1.5179615021 
0.7294106717  0.7076119225  0.8079299691  0.6907216495  0.7299541810  0.6632302405  0.8181306306  0.7688838782  0.7332185886  0.7256027555  4.9433573635  6.2923591971  2.2550172806  300           0.1542945464 
0.8014307513  0.7947144552  0.9346035015  0.7793814433  0.8591065292  0.7445589920  0.9222972973  0.8602029312  0.8152610442  0.7876004592  9.8867147271  3.3834559560  2.2550172806  600           0.1764269288 
0.8176427207  0.8131325456  0.9763130793  0.7835051546  0.9072164948  0.7697594502  0.9527027027  0.8861330327  0.8327596099  0.8025258324  14.830072090  2.5158896796  2.2550172806  900           0.1784038146 
0.8240994151  0.8293440569  0.9835221421  0.8082474227  0.9312714777  0.7835051546  0.9707207207  0.8962795941  0.8376362593  0.8105625718  19.773429454  2.0966438452  2.2550172806  1200          0.1765007369 
0.8305570976  0.8304895322  0.9881565396  0.8082474227  0.9475945017  0.7869415808  0.9766328829  0.8962795941  0.8390705680  0.8220436280  24.716786817  1.8936383482  2.2550172806  1500          0.1761248581 
0.8318483047  0.8365042896  0.9897013388  0.8103092784  0.9536082474  0.7995418099  0.9817004505  0.8996617813  0.8405048766  0.8231917336  29.660144181  1.7569763692  2.2550172806  1800          0.1743591054 
0.8319914062  0.8345831108  0.9912461380  0.8000000000  0.9653493700  0.8018327606  0.9825450450  0.9019165727  0.8419391853  0.8220436280  34.603501544  1.6750246016  2.2550172806  2100          0.1776673460 
0.8358660157  0.8402039899  0.9938208033  0.8123711340  0.9690721649  0.8006872852  0.9867680180  0.9075535513  0.8427997705  0.8289322618  39.546858908  1.5948527221  2.2550172806  2400          0.1826113915 
0.8374444139  0.8368680350  0.9927909372  0.8103092784  0.9699312715  0.7972508591  0.9876126126  0.9030439684  0.8436603557  0.8312284730  44.490216271  1.5480579722  2.2550172806  2700          0.1784014130 
0.8383053285  0.8401517311  0.9927909372  0.8144329897  0.9742268041  0.8029782360  0.9893018018  0.9030439684  0.8442340792  0.8323765786  49.433573635  1.5117268316  2.2550172806  3000          0.1800562072 
0.8401709178  0.8413253591  0.9933058702  0.8123711340  0.9745131730  0.7995418099  0.9921171171  0.9120631342  0.8445209409  0.8358208955  54.376930999  1.4632390952  2.2550172806  3300          0.1779000417 
0.8408880721  0.8481097932  0.9938208033  0.8144329897  0.9765177549  0.8155784651  0.9926801802  0.9143179256  0.8459552496  0.8358208955  59.320288362  1.4350653652  2.2550172806  3600          0.1789665373 
0.8421792793  0.8441508650  0.9953656025  0.8082474227  0.9790950745  0.8121420389  0.9923986486  0.9120631342  0.8473895582  0.8369690011  64.263645726  1.3277689099  5.3968892097  3900          0.1995185939 
0.8417486573  0.8353809402  0.9943357364  0.7979381443  0.9779495991  0.7983963345  0.9954954955  0.9098083427  0.8476764200  0.8358208955  69.207003089  1.1067796369  5.3968892097  4200          0.2190927720 
0.8444748318  0.8443920132  0.9948506694  0.8123711340  0.9819587629  0.8109965636  0.9932432432  0.9098083427  0.8496844521  0.8392652124  74.150360453  1.0357193593  5.3968892097  4500          0.2205180963 
0.8447616936  0.8416488988  0.9943357364  0.8144329897  0.9810996564  0.8018327606  0.9926801802  0.9086809470  0.8502581756  0.8392652124  79.093717816  0.9932184486  5.3968892097  4800          0.2216562112 
0.8444745025  0.8409435339  0.9953656025  0.8123711340  0.9799541810  0.7983963345  0.9946509009  0.9120631342  0.8508318990  0.8381171068  82.389289392  0.9632119194  5.3968892097  5000          0.2215642798 
