Epoch: 0001 train_loss= 1.39226 train_acc= 0.30664 val_loss= 1.39542 val_acc= 0.26786 time= 0.21830
Epoch: 0002 train_loss= 1.38616 train_acc= 0.27734 val_loss= 1.39069 val_acc= 0.26786 time= 0.01562
Epoch: 0003 train_loss= 1.38613 train_acc= 0.28125 val_loss= 1.38774 val_acc= 0.26786 time= 0.01563
Epoch: 0004 train_loss= 1.38463 train_acc= 0.29688 val_loss= 1.38518 val_acc= 0.25000 time= 0.01563
Epoch: 0005 train_loss= 1.38347 train_acc= 0.29883 val_loss= 1.38267 val_acc= 0.26786 time= 0.01563
Epoch: 0006 train_loss= 1.38276 train_acc= 0.29297 val_loss= 1.38059 val_acc= 0.28571 time= 0.01563
Epoch: 0007 train_loss= 1.38616 train_acc= 0.30859 val_loss= 1.37986 val_acc= 0.26786 time= 0.01563
Epoch: 0008 train_loss= 1.38454 train_acc= 0.29297 val_loss= 1.37955 val_acc= 0.26786 time= 0.01563
Epoch: 0009 train_loss= 1.38239 train_acc= 0.30664 val_loss= 1.37969 val_acc= 0.26786 time= 0.01563
Epoch: 0010 train_loss= 1.38239 train_acc= 0.29297 val_loss= 1.37996 val_acc= 0.26786 time= 0.01563
Epoch: 0011 train_loss= 1.38207 train_acc= 0.28906 val_loss= 1.38033 val_acc= 0.25000 time= 0.01563
Epoch: 0012 train_loss= 1.38167 train_acc= 0.28711 val_loss= 1.38091 val_acc= 0.26786 time= 0.01563
Epoch: 0013 train_loss= 1.38354 train_acc= 0.28711 val_loss= 1.38172 val_acc= 0.26786 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.39303 accuracy= 0.31858 time= 0.01563 
