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: [2]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: VLCS
	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/ceb4753c3d4776000a5e3bff7150bed4
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1949993959
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	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 normal 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    
0.0916207298  0.1989134146  0.1024734982  0.1130742049  0.2875294118  0.3088512241  0.0872048743  0.0960365854  0.1780821918  0.1748148148  0.0000000000  5.5084972382  2.0073552132  0             1.6574947834 
0.8013364243  0.8570412217  1.0000000000  1.0000000000  0.7454117647  0.7118644068  0.7932216299  0.8094512195  0.9155868197  0.8592592593  8.4805653710  1.9956462447  2.2543764114  300           0.6273391509 
0.8015274084  0.8674808586  1.0000000000  0.9964664311  0.7849411765  0.7363465160  0.7920792079  0.8109756098  0.9448352462  0.8696296296  16.961130742  1.3831838477  2.2543764114  600           0.6222644607 
0.8043846243  0.8676924143  1.0000000000  0.9929328622  0.8014117647  0.7419962335  0.7947448591  0.8140243902  0.9589041096  0.8681481481  25.441696113  1.2680245217  2.2543764114  900           0.6385414688 
0.8032416218  0.8727851012  1.0000000000  1.0000000000  0.8169411765  0.7457627119  0.7939832445  0.8125000000  0.9696408738  0.8725925926  33.922261484  1.1865048462  2.2543764114  1200          0.6391675695 
0.8017189731  0.8665289910  1.0000000000  0.9929328622  0.8409411765  0.7325800377  0.7894135567  0.8140243902  0.9748241392  0.8740740741  42.402826855  1.0608894442  2.2543764114  1500          0.6447021643 
0.8009567780  0.8740763807  1.0000000000  0.9964664311  0.8555294118  0.7457627119  0.7894135567  0.8125000000  0.9807478712  0.8800000000  50.883392226  1.0284997173  2.2543764114  1800          0.6334988793 
0.8000041792  0.8693222480  1.0000000000  0.9964664311  0.8668235294  0.7344632768  0.7890327494  0.8109756098  0.9822288041  0.8770370370  59.363957597  0.9879607006  2.2543764114  2100          0.6278004853 
0.7977193353  0.8718750834  1.0000000000  0.9964664311  0.8823529412  0.7495291902  0.7844630617  0.8109756098  0.9907441688  0.8696296296  67.844522968  1.0337191908  2.2543764114  2400          0.6372459022 
0.7952423463  0.8720592223  1.0000000000  0.9964664311  0.8931764706  0.7382297552  0.7840822544  0.8064024390  0.9888930026  0.8814814815  76.325088339  0.9792338216  2.2543764114  2700          0.6480636009 
0.7931467451  0.8771374762  1.0000000000  1.0000000000  0.9030588235  0.7514124294  0.7829398324  0.8033536585  0.9914846353  0.8800000000  84.805653710  0.9626421052  2.2543764114  3000          0.6312923813 
0.7937185366  0.8694059476  1.0000000000  0.9964664311  0.9129411765  0.7495291902  0.7825590251  0.8048780488  0.9914846353  0.8622222222  93.286219081  0.9550210430  2.2543764114  3300          0.6358540161 
0.7944807317  0.8797823810  1.0000000000  1.0000000000  0.9223529412  0.7608286252  0.7825590251  0.8064024390  0.9922251018  0.8785185185  101.76678445  0.9393297132  2.2543764114  3600          0.6417529655 
0.7942903280  0.8736662531  1.0000000000  0.9964664311  0.9256470588  0.7608286252  0.7821782178  0.8064024390  0.9911144021  0.8637037037  110.24734982  0.6787911168  5.3971567154  3900          0.6386106443 
0.7956243146  0.8704498846  1.0000000000  1.0000000000  0.9280000000  0.7476459510  0.7817974105  0.8094512195  0.9911144021  0.8637037037  118.72791519  0.4453689722  5.3971567154  4200          0.6452230692 
0.7948621195  0.8719671528  1.0000000000  0.9964664311  0.9284705882  0.7438794727  0.7817974105  0.8079268293  0.9962976675  0.8755555556  127.20848056  0.4253149803  5.3971567154  4500          0.6305025943 
0.7950531036  0.8732226456  1.0000000000  0.9964664311  0.9392941176  0.7476459510  0.7806549886  0.8094512195  0.9948167345  0.8755555556  135.68904593  0.4152781243  5.3971567154  4800          0.6423246264 
0.7950536841  0.8737727555  1.0000000000  1.0000000000  0.9421176471  0.7457627119  0.7791317593  0.8109756098  0.9959274343  0.8755555556  141.34275618  0.4096726850  5.3971567154  5000          0.6459195721 
