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/bf3d76e75b644d17f7f1365efdb8ac24
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 677429476
	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: 0.7819049321936025
	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 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    
0.0186139748  0.0199066206  0.0221421215  0.0288659794  0.0177548683  0.0194730813  0.0163288288  0.0078917700  0.0197934596  0.0229621125  0.0000000000  10.825601577  2.0088801384  0             1.5342926979 
0.4843928978  0.8085005601  0.8759011329  0.7567010309  0.4876861397  0.4810996564  0.8975225225  0.8421645998  0.8723465290  0.8266360505  4.9433573635  5.8977976783  2.2550172806  300           0.3316438683 
0.5524054980  0.8724664846  0.9691040165  0.8350515464  0.5641466208  0.5406643757  0.9611486486  0.9109357384  0.9520940906  0.8714121699  9.8867147271  3.0325719245  2.2550172806  600           0.3108199739 
0.5632875140  0.8809492503  0.9830072091  0.8432989691  0.5767468499  0.5498281787  0.9766328829  0.9120631342  0.9704532415  0.8874856487  14.830072090  2.3303734819  2.2550172806  900           0.3223099311 
0.5650057271  0.8897952028  0.9927909372  0.8597938144  0.5790378007  0.5509736541  0.9825450450  0.9278466742  0.9767641997  0.8817451206  19.773429454  2.0075735203  2.2550172806  1200          0.3210576868 
0.5654352804  0.8914950665  0.9948506694  0.8659793814  0.5776059565  0.5532646048  0.9893018018  0.9244644870  0.9856569134  0.8840413318  24.716786817  1.8648439880  2.2550172806  1500          0.3179862754 
0.5680125999  0.8913467202  0.9933058702  0.8597938144  0.5816151203  0.5544100802  0.9907094595  0.9244644870  0.9868043603  0.8897818599  29.660144181  1.7771736471  2.2550172806  1800          0.3093186879 
0.5678694155  0.8987180790  0.9938208033  0.8659793814  0.5813287514  0.5544100802  0.9935247748  0.9323562570  0.9902467011  0.8978185993  34.603501544  1.6822995023  2.2550172806  2100          0.3155966043 
0.5670103090  0.8917225187  0.9969104016  0.8597938144  0.5807560137  0.5532646048  0.9923986486  0.9255918828  0.9902467011  0.8897818599  39.546858908  1.6251459157  2.2550172806  2400          0.3094160453 
0.5668671246  0.8928361079  0.9953656025  0.8597938144  0.5804696449  0.5532646048  0.9929617117  0.9312288613  0.9925415950  0.8874856487  44.490216271  1.5723270170  2.2550172806  2700          0.3078138177 
0.5678694155  0.8969331934  0.9953656025  0.8618556701  0.5824742268  0.5532646048  0.9954954955  0.9368658399  0.9951233505  0.8920780712  49.433573635  1.5196242857  2.2550172806  3000          0.3210749380 
0.5694444442  0.8946991119  0.9953656025  0.8618556701  0.5833333333  0.5555555556  0.9954954955  0.9267192785  0.9951233505  0.8955223881  54.376930999  1.4700330671  2.2550172806  3300          0.3197195148 
0.5707331040  0.8943876253  0.9953656025  0.8597938144  0.5836197022  0.5578465063  0.9952139640  0.9278466742  0.9956970740  0.8955223881  59.320288362  1.4283402646  2.2550172806  3600          0.3130128694 
0.5694444442  0.8998602687  0.9953656025  0.8556701031  0.5810423826  0.5578465063  0.9954954955  0.9346110485  0.9962707975  0.9092996556  64.263645726  1.3731605117  5.3966603279  3900          0.3138227646 
0.5687285221  0.8949186734  0.9953656025  0.8659793814  0.5819014891  0.5555555556  0.9926801802  0.9278466742  0.9956970740  0.8909299656  69.207003089  1.1525115875  5.3966603279  4200          0.3088743981 
0.5678694155  0.8991581895  0.9963954686  0.8639175258  0.5824742268  0.5532646048  0.9952139640  0.9357384442  0.9956970740  0.8978185993  74.150360453  1.0698979658  5.3966603279  4500          0.3043569263 
0.5675830467  0.8950096111  0.9948506694  0.8742268041  0.5841924399  0.5509736541  0.9954954955  0.9244644870  0.9954102123  0.8863375431  79.093717816  1.0164946107  5.3966603279  4800          0.3100084782 
0.5680125999  0.8974413495  0.9969104016  0.8701030928  0.5850515464  0.5509736541  0.9963400901  0.9278466742  0.9959839357  0.8943742824  82.389289392  0.9807868984  5.3966603279  5000          0.3220312250 
