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: 1
	output_dir: sweep/ablation3/outputs/f40d02a40506c55df1580a78701699b2
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1249790725
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [3]
	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: 0.7819049321936025
	lambda2: 0.9075316444347157
	last_k_epoch: 0.25491468830584113
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.907263233121133
	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    
0.0223811434  0.0279516653  0.0211122554  0.0247422680  0.0203321879  0.0309278351  0.0264639640  0.0281848929  0.0240963855  0.0206659013  0.0000000000  10.994625091  2.0088801384  0             1.4669451714 
0.7797713731  0.7454488552  0.8583934089  0.7463917526  0.7686139748  0.6849942726  0.8620495495  0.8049605411  0.7765347103  0.7830080367  4.9433573635  6.0281775562  2.2589011192  300           0.1563810809 
0.8216640545  0.8296575237  0.9613800206  0.8226804124  0.8951890034  0.7857961054  0.9524211712  0.8804960541  0.8224325875  0.8208955224  9.8867147271  3.3026730982  2.2589011192  600           0.1838677931 
0.8282641798  0.8403044611  0.9855818744  0.8309278351  0.9369988545  0.7869415808  0.9729729730  0.9030439684  0.8275960987  0.8289322618  14.830072090  2.4608021069  2.2589011192  900           0.1790587409 
0.8321378012  0.8442513362  0.9886714727  0.8268041237  0.9547537228  0.7983963345  0.9819819820  0.9075535513  0.8318990247  0.8323765786  19.773429454  2.0969196117  2.2589011192  1200          0.1793716367 
0.8354380286  0.8499204277  0.9927909372  0.8391752577  0.9607674685  0.8064146621  0.9836711712  0.9041713641  0.8339070568  0.8369690011  24.716786817  1.9112595300  2.2589011192  1500          0.1807041820 
0.8358673331  0.8519642037  0.9948506694  0.8350515464  0.9684994273  0.8132875143  0.9893018018  0.9075535513  0.8382099828  0.8335246843  29.660144181  1.7736552922  2.2589011192  1800          0.1819854291 
0.8368713492  0.8453144200  0.9958805355  0.8185567010  0.9745131730  0.8087056128  0.9921171171  0.9086809470  0.8402180149  0.8335246843  34.603501544  1.6662707539  2.2589011192  2100          0.1836500947 
0.8381628857  0.8509172194  0.9953656025  0.8309278351  0.9762313860  0.8041237113  0.9932432432  0.9177001127  0.8405048766  0.8358208955  39.546858908  1.6186853588  2.2589011192  2400          0.1799561143 
0.8394540928  0.8671287307  0.9948506694  0.8556701031  0.9765177549  0.8178694158  0.9898648649  0.9278466742  0.8419391853  0.8369690011  44.490216271  1.5620944754  2.2589011192  2700          0.1848245645 
0.8434714745  0.8574564590  0.9948506694  0.8412371134  0.9796678121  0.8224513173  0.9940878378  0.9086809470  0.8453815261  0.8415614237  49.433573635  1.5274721658  2.2589011192  3000          0.1846222202 
0.8451933035  0.8577659654  0.9953656025  0.8309278351  0.9831042383  0.8201603666  0.9952139640  0.9222096956  0.8465289730  0.8438576349  54.376930999  1.4781425548  2.2589011192  3300          0.1835144734 
0.8449064418  0.8592992925  0.9958805355  0.8412371134  0.9833906071  0.8155784651  0.9949324324  0.9210822999  0.8459552496  0.8438576349  59.320288362  1.4427937166  2.2589011192  3600          0.1793033671 
0.8443320597  0.8576373416  0.9958805355  0.8350515464  0.9833906071  0.8201603666  0.9946509009  0.9177001127  0.8471026965  0.8415614237  64.263645726  1.3624282598  5.3998646736  3900          0.2047024393 
0.8447626816  0.8578242508  0.9979402678  0.8288659794  0.9836769759  0.8190148912  0.9957770270  0.9255918828  0.8468158348  0.8427095293  69.207003089  1.1702068988  5.3998646736  4200          0.2236482835 
0.8472019944  0.8626352474  0.9969104016  0.8329896907  0.9868270332  0.8293241695  0.9966216216  0.9255918828  0.8482501434  0.8461538462  74.150360453  1.0930525023  5.3998646736  4500          0.2219830465 
0.8472019944  0.8556277448  0.9969104016  0.8268041237  0.9836769759  0.8178694158  0.9966216216  0.9222096956  0.8482501434  0.8461538462  79.093717816  1.0412743773  5.3998646736  4800          0.2222126460 
0.8479194780  0.8680631907  0.9974253347  0.8412371134  0.9848224513  0.8384879725  0.9957770270  0.9244644870  0.8485370052  0.8473019518  82.389289392  1.0012403893  5.3998646736  5000          0.2211829603 
