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: 3
	output_dir: sweep/ablation3/outputs/d0dee21536ec9fee49fe976d5f58b448
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 758829802
	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: 0.8610090196552951
	lambda2: 0.5777772877463595
	last_k_epoch: 0.32350558703299503
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 2.866557071912062
	weight_decay: 0.0001
	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    
0.0131729668  0.0183353808  0.0185375901  0.0185567010  0.0126002291  0.0137457045  0.0166103604  0.0157835400  0.0154905336  0.0206659013  0.0000000000  10.783355712  2.0088801384  0             1.5705969334 
0.4958476515  0.7871509000  0.8496395469  0.7484536082  0.4899770905  0.5017182131  0.8941441441  0.8173618940  0.8775100402  0.7956371986  4.9433573635  5.4924299677  2.2589011192  300           0.3035788925 
0.5451030925  0.8637412653  0.9675592173  0.8247422680  0.5529782360  0.5372279496  0.9591779279  0.8996617813  0.9472174412  0.8668197474  9.8867147271  2.7163574855  2.2589011192  600           0.3000425784 
0.5519759447  0.8696865609  0.9871266735  0.8391752577  0.5587056128  0.5452462772  0.9752252252  0.9019165727  0.9672977625  0.8679678530  14.830072090  2.0467731023  2.2589011192  900           0.2982138133 
0.5582760593  0.8771232190  0.9886714727  0.8329896907  0.5655784651  0.5509736541  0.9833896396  0.9131905299  0.9790590935  0.8851894374  19.773429454  1.7653168162  2.2589011192  1200          0.3055054482 
0.5614261166  0.8833661947  0.9917610711  0.8494845361  0.5672966781  0.5555555556  0.9859234234  0.9165727170  0.9836488812  0.8840413318  24.716786817  1.6336231895  2.2589011192  1500          0.3044199975 
0.5652920959  0.8846328512  0.9933058702  0.8577319588  0.5681557847  0.5624284078  0.9878941441  0.9086809470  0.9893861159  0.8874856487  29.660144181  1.5790196407  2.2589011192  1800          0.3043434215 
0.5645761738  0.8835926595  0.9963954686  0.8536082474  0.5701603666  0.5589919817  0.9909909910  0.9165727170  0.9905335628  0.8805970149  34.603501544  1.5082401200  2.2589011192  2100          0.3051054732 
0.5685853376  0.8892503480  0.9948506694  0.8536082474  0.5735967927  0.5635738832  0.9912725225  0.9301014656  0.9916810098  0.8840413318  39.546858908  1.4513988221  2.2589011192  2400          0.3002548059 
0.5681557844  0.8932395196  0.9927909372  0.8597938144  0.5715922108  0.5647193585  0.9932432432  0.9278466742  0.9942627653  0.8920780712  44.490216271  1.4107048285  2.2589011192  2700          0.3120962890 
0.5691580753  0.8936658235  0.9953656025  0.8577319588  0.5747422680  0.5635738832  0.9932432432  0.9334836528  0.9948364888  0.8897818599  49.433573635  1.3671534836  2.2589011192  3000          0.3122682198 
0.5694444442  0.8934788036  0.9963954686  0.8742268041  0.5741695304  0.5647193585  0.9938063063  0.9244644870  0.9965576592  0.8817451206  54.376930999  1.3467202715  2.2589011192  3300          0.3003224786 
0.5704467351  0.8886411813  0.9953656025  0.8494845361  0.5750286369  0.5658648339  0.9943693694  0.9301014656  0.9951233505  0.8863375431  59.320288362  1.1947030004  5.3998646736  3600          0.3108671419 
0.5724513170  0.8902964555  0.9963954686  0.8680412371  0.5767468499  0.5681557847  0.9957770270  0.9199549042  0.9962707975  0.8828932262  64.263645726  1.0138600709  5.3998646736  3900          0.3099415072 
0.5737399768  0.8971643794  0.9958805355  0.8680412371  0.5770332188  0.5704467354  0.9949324324  0.9233370913  0.9948364888  0.9001148106  69.207003089  0.9421086444  5.3998646736  4200          0.3010534732 
0.5725945014  0.8960460691  0.9969104016  0.8659793814  0.5781786942  0.5670103093  0.9946509009  0.9312288613  0.9968445209  0.8909299656  74.150360453  0.8984750841  5.3998646736  4500          0.3054322656 
0.5748854522  0.8959344216  0.9953656025  0.8577319588  0.5793241695  0.5704467354  0.9960585586  0.9379932356  0.9965576592  0.8920780712  79.093717816  0.8664339288  5.3998646736  4800          0.3007428972 
0.5750286366  0.8876759385  0.9974253347  0.8556701031  0.5784650630  0.5715922108  0.9946509009  0.9244644870  0.9962707975  0.8828932262  82.389289392  0.8445362720  5.3998646736  5000          0.2953597391 
