Epoch: 0001 train_loss= 1.42611 train_acc= 0.26710 val_loss= 1.37476 val_acc= 0.39286 time= 0.14064
Epoch: 0002 train_loss= 1.38686 train_acc= 0.31270 val_loss= 1.36690 val_acc= 0.39286 time= 0.01562
Epoch: 0003 train_loss= 1.40585 train_acc= 0.32899 val_loss= 1.36630 val_acc= 0.39286 time= 0.00000
Epoch: 0004 train_loss= 1.40794 train_acc= 0.34528 val_loss= 1.36855 val_acc= 0.39286 time= 0.01563
Epoch: 0005 train_loss= 1.40704 train_acc= 0.32573 val_loss= 1.37305 val_acc= 0.39286 time= 0.01563
Epoch: 0006 train_loss= 1.39866 train_acc= 0.30619 val_loss= 1.37511 val_acc= 0.39286 time= 0.01563
Epoch: 0007 train_loss= 1.38754 train_acc= 0.30945 val_loss= 1.37594 val_acc= 0.39286 time= 0.01563
Epoch: 0008 train_loss= 1.39241 train_acc= 0.26059 val_loss= 1.37611 val_acc= 0.39286 time= 0.01563
Epoch: 0009 train_loss= 1.38571 train_acc= 0.32899 val_loss= 1.37666 val_acc= 0.39286 time= 0.01563
Epoch: 0010 train_loss= 1.40443 train_acc= 0.32573 val_loss= 1.37666 val_acc= 0.39286 time= 0.00000
Epoch: 0011 train_loss= 1.38248 train_acc= 0.32573 val_loss= 1.37670 val_acc= 0.39286 time= 0.01563
Epoch: 0012 train_loss= 1.36783 train_acc= 0.33876 val_loss= 1.37658 val_acc= 0.39286 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38696 accuracy= 0.27434 time= 0.00000 
