Epoch: 0001 train_loss= 2.13468 train_acc= 0.09434 val_loss= 2.10763 val_acc= 0.13793 time= 0.13103
Epoch: 0002 train_loss= 2.10182 train_acc= 0.10692 val_loss= 2.10673 val_acc= 0.17241 time= 0.01563
Epoch: 0003 train_loss= 2.10996 train_acc= 0.14465 val_loss= 2.10679 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.10437 train_acc= 0.08805 val_loss= 2.10616 val_acc= 0.10345 time= 0.01562
Epoch: 0005 train_loss= 2.08912 train_acc= 0.16981 val_loss= 2.10542 val_acc= 0.06897 time= 0.00000
Epoch: 0006 train_loss= 2.08113 train_acc= 0.13836 val_loss= 2.10527 val_acc= 0.06897 time= 0.01563
Epoch: 0007 train_loss= 2.08821 train_acc= 0.13208 val_loss= 2.10573 val_acc= 0.03448 time= 0.00000
Epoch: 0008 train_loss= 2.07049 train_acc= 0.23899 val_loss= 2.10715 val_acc= 0.03448 time= 0.01563
Epoch: 0009 train_loss= 2.05482 train_acc= 0.17610 val_loss= 2.10937 val_acc= 0.06897 time= 0.00000
Epoch: 0010 train_loss= 2.05087 train_acc= 0.18868 val_loss= 2.11224 val_acc= 0.03448 time= 0.01563
Epoch: 0011 train_loss= 2.03817 train_acc= 0.19497 val_loss= 2.11546 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.03631 train_acc= 0.18868 val_loss= 2.11898 val_acc= 0.03448 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 2.07145 accuracy= 0.15254 time= 0.00000 
