Epoch: 0001 train_loss= 1.44304 train_acc= 0.23633 val_loss= 1.39181 val_acc= 0.23214 time= 0.18751
Epoch: 0002 train_loss= 1.42976 train_acc= 0.23828 val_loss= 1.38380 val_acc= 0.25000 time= 0.01563
Epoch: 0003 train_loss= 1.40271 train_acc= 0.23828 val_loss= 1.37861 val_acc= 0.25000 time= 0.01563
Epoch: 0004 train_loss= 1.40408 train_acc= 0.23828 val_loss= 1.37365 val_acc= 0.35714 time= 0.03125
Epoch: 0005 train_loss= 1.39625 train_acc= 0.22656 val_loss= 1.36994 val_acc= 0.35714 time= 0.01563
Epoch: 0006 train_loss= 1.39018 train_acc= 0.25586 val_loss= 1.36731 val_acc= 0.35714 time= 0.01563
Epoch: 0007 train_loss= 1.39143 train_acc= 0.31055 val_loss= 1.36603 val_acc= 0.35714 time= 0.01563
Epoch: 0008 train_loss= 1.38586 train_acc= 0.31445 val_loss= 1.36497 val_acc= 0.35714 time= 0.01563
Epoch: 0009 train_loss= 1.38596 train_acc= 0.31250 val_loss= 1.36492 val_acc= 0.35714 time= 0.01563
Epoch: 0010 train_loss= 1.38680 train_acc= 0.31055 val_loss= 1.36517 val_acc= 0.35714 time= 0.01563
Epoch: 0011 train_loss= 1.38603 train_acc= 0.31445 val_loss= 1.36610 val_acc= 0.35714 time= 0.01563
Epoch: 0012 train_loss= 1.38800 train_acc= 0.31250 val_loss= 1.36733 val_acc= 0.35714 time= 0.01563
Epoch: 0013 train_loss= 1.38444 train_acc= 0.31055 val_loss= 1.36839 val_acc= 0.35714 time= 0.01563
Epoch: 0014 train_loss= 1.39178 train_acc= 0.31250 val_loss= 1.36964 val_acc= 0.39286 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.41429 accuracy= 0.27434 time= 0.00000 
