Epoch: 0001 train_loss= 2.10007 train_acc= 0.09434 val_loss= 2.10510 val_acc= 0.06897 time= 0.69015
Epoch: 0002 train_loss= 2.10033 train_acc= 0.12129 val_loss= 2.10417 val_acc= 0.06897 time= 0.01100
Epoch: 0003 train_loss= 2.07697 train_acc= 0.15633 val_loss= 2.10356 val_acc= 0.06897 time= 0.01200
Epoch: 0004 train_loss= 2.07205 train_acc= 0.18329 val_loss= 2.10337 val_acc= 0.06897 time= 0.01000
Epoch: 0005 train_loss= 2.06256 train_acc= 0.14825 val_loss= 2.10289 val_acc= 0.06897 time= 0.01100
Epoch: 0006 train_loss= 2.06009 train_acc= 0.16712 val_loss= 2.10234 val_acc= 0.06897 time= 0.00900
Epoch: 0007 train_loss= 2.06177 train_acc= 0.18868 val_loss= 2.10250 val_acc= 0.06897 time= 0.00900
Epoch: 0008 train_loss= 2.05413 train_acc= 0.18598 val_loss= 2.10282 val_acc= 0.06897 time= 0.01100
Epoch: 0009 train_loss= 2.05199 train_acc= 0.18868 val_loss= 2.10302 val_acc= 0.06897 time= 0.01000
Epoch: 0010 train_loss= 2.05144 train_acc= 0.18329 val_loss= 2.10336 val_acc= 0.06897 time= 0.00900
Epoch: 0011 train_loss= 2.04058 train_acc= 0.20755 val_loss= 2.10423 val_acc= 0.06897 time= 0.01100
Epoch: 0012 train_loss= 2.05686 train_acc= 0.19677 val_loss= 2.10530 val_acc= 0.06897 time= 0.01000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07543 accuracy= 0.15254 time= 0.00600 
