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/cc75387b8040577ad020489bfa1b615e
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1318935739
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [1]
	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: 0.5694511041907044
	lambda2: 0.6621108818243455
	last_k_epoch: 0.20248994529588413
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.502579147595572
	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    
0.0118843070  0.0179457756  0.0113285273  0.0185567010  0.0100229095  0.0137457045  0.0146396396  0.0169109357  0.0200803213  0.0183696900  0.0000000000  7.7819032669  1.7954735756  0             1.5647356510 
0.4720790376  0.7781163762  0.8671472709  0.7340206186  0.4733676976  0.4707903780  0.8668355856  0.8196166855  0.8528399312  0.7807118255  4.9433573635  5.1520903627  2.0968332291  300           0.3013878894 
0.5395189001  0.8494822602  0.9691040165  0.8082474227  0.5337915235  0.5452462772  0.9557995495  0.8928974070  0.9486517499  0.8473019518  9.8867147271  2.6861491688  2.0968332291  600           0.2912398092 
0.5438144327  0.8667050393  0.9860968074  0.8164948454  0.5446735395  0.5429553265  0.9774774775  0.9041713641  0.9704532415  0.8794489093  14.830072090  1.9187804004  2.0968332291  900           0.3028720999 
0.5498281784  0.8653087715  0.9938208033  0.8226804124  0.5463917526  0.5532646048  0.9856418919  0.9064261556  0.9804934022  0.8668197474  19.773429454  1.5838849632  2.0968332291  1200          0.2971876677 
0.5541237111  0.8791941602  0.9953656025  0.8371134021  0.5515463918  0.5567010309  0.9898648649  0.9244644870  0.9879518072  0.8760045924  24.716786817  1.4130944502  2.0968332291  1500          0.3086849912 
0.5591351658  0.8743028629  0.9953656025  0.8268041237  0.5558419244  0.5624284078  0.9915540541  0.9120631342  0.9911072863  0.8840413318  29.660144181  1.2982710274  2.0968332291  1800          0.2992537872 
0.5624284075  0.8770312939  0.9938208033  0.8350515464  0.5567010309  0.5681557847  0.9926801802  0.9154453213  0.9931153184  0.8805970149  34.603501544  1.2463241619  2.0968332291  2100          0.2971513828 
0.5651489115  0.8771382204  0.9938208033  0.8412371134  0.5621420389  0.5681557847  0.9943693694  0.9222096956  0.9945496271  0.8679678530  39.546858908  1.2214681445  2.0968332291  2400          0.3010006571 
0.5680125999  0.8767979258  0.9953656025  0.8309278351  0.5632875143  0.5727376861  0.9943693694  0.9165727170  0.9956970740  0.8828932262  44.490216271  1.1598564712  2.0968332291  2700          0.2999432254 
0.5691580753  0.8823536162  0.9963954686  0.8453608247  0.5644329897  0.5738831615  0.9960585586  0.9199549042  0.9959839357  0.8817451206  49.433573635  1.1447684604  2.0968332291  3000          0.3090392836 
0.5725945014  0.8804341910  0.9958805355  0.8350515464  0.5690148912  0.5761741123  0.9971846847  0.9222096956  0.9977051061  0.8840413318  54.376930999  1.1220509360  2.0968332291  3300          0.3050434963 
0.5733104235  0.8865012071  0.9948506694  0.8453608247  0.5681557847  0.5784650630  0.9946509009  0.9301014656  0.9974182444  0.8840413318  59.320288362  1.0827871573  2.0968332291  3600          0.3036578329 
0.5763172964  0.8837153675  0.9958805355  0.8391752577  0.5695876289  0.5830469645  0.9957770270  0.9233370913  0.9979919679  0.8886337543  64.263645726  1.0582095951  2.0968332291  3900          0.3061486046 
0.5771764029  0.8830647810  0.9953656025  0.8350515464  0.5724513173  0.5819014891  0.9957770270  0.9301014656  0.9968445209  0.8840413318  69.207003089  0.9318619887  5.4022812843  4200          0.3003042229 
0.5781786939  0.8807180644  0.9958805355  0.8371134021  0.5756013746  0.5807560137  0.9963400901  0.9255918828  0.9977051061  0.8794489093  74.150360453  0.8116564278  5.4022812843  4500          0.3020278708 
0.5798969069  0.8856426835  0.9958805355  0.8391752577  0.5767468499  0.5830469645  0.9971846847  0.9210822999  0.9965576592  0.8966704937  79.093717816  0.7635110893  5.4022812843  4800          0.3093866404 
0.5791809848  0.8873999558  0.9948506694  0.8432989691  0.5764604811  0.5819014891  0.9960585586  0.9210822999  0.9977051061  0.8978185993  82.389289392  0.7275190791  5.4022812843  5000          0.3065691841 
