Epoch: 0001 train_loss= 0.68918 train_acc= 0.53766 val_loss= 0.69392 val_acc= 0.50820 time= 0.89068
Epoch: 0002 train_loss= 0.68978 train_acc= 0.54026 val_loss= 0.69478 val_acc= 0.50820 time= 0.00000
Epoch: 0003 train_loss= 0.68907 train_acc= 0.53506 val_loss= 0.69485 val_acc= 0.50820 time= 0.01563
Epoch: 0004 train_loss= 0.69012 train_acc= 0.53766 val_loss= 0.69461 val_acc= 0.50820 time= 0.00000
Epoch: 0005 train_loss= 0.69199 train_acc= 0.53506 val_loss= 0.69423 val_acc= 0.50820 time= 0.00000
Epoch: 0006 train_loss= 0.68839 train_acc= 0.53636 val_loss= 0.69389 val_acc= 0.50820 time= 0.01591
Epoch: 0007 train_loss= 0.69114 train_acc= 0.53636 val_loss= 0.69359 val_acc= 0.50820 time= 0.00600
Epoch: 0008 train_loss= 0.69096 train_acc= 0.53506 val_loss= 0.69335 val_acc= 0.50820 time= 0.00500
Epoch: 0009 train_loss= 0.69150 train_acc= 0.53636 val_loss= 0.69318 val_acc= 0.50820 time= 0.00420
Epoch: 0010 train_loss= 0.69248 train_acc= 0.53636 val_loss= 0.69300 val_acc= 0.50820 time= 0.00000
Epoch: 0011 train_loss= 0.69079 train_acc= 0.53377 val_loss= 0.69291 val_acc= 0.50820 time= 0.00000
Epoch: 0012 train_loss= 0.68968 train_acc= 0.53896 val_loss= 0.69291 val_acc= 0.50820 time= 0.01562
Epoch: 0013 train_loss= 0.69233 train_acc= 0.53766 val_loss= 0.69290 val_acc= 0.50820 time= 0.00000
Epoch: 0014 train_loss= 0.69209 train_acc= 0.53766 val_loss= 0.69292 val_acc= 0.50820 time= 0.00000
Epoch: 0015 train_loss= 0.69078 train_acc= 0.53506 val_loss= 0.69300 val_acc= 0.50820 time= 0.01563
Epoch: 0016 train_loss= 0.69033 train_acc= 0.53636 val_loss= 0.69308 val_acc= 0.50820 time= 0.00000
Epoch: 0017 train_loss= 0.68969 train_acc= 0.53766 val_loss= 0.69318 val_acc= 0.50820 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.70407 accuracy= 0.44262 time= 0.01563 
