Epoch: 0001 train_loss= 1.39293 train_acc= 0.24609 val_loss= 1.39086 val_acc= 0.28571 time= 0.32647
Epoch: 0002 train_loss= 1.39067 train_acc= 0.26172 val_loss= 1.39032 val_acc= 0.25000 time= 0.01563
Epoch: 0003 train_loss= 1.38865 train_acc= 0.31250 val_loss= 1.38990 val_acc= 0.25000 time= 0.00000
Epoch: 0004 train_loss= 1.38714 train_acc= 0.31836 val_loss= 1.38961 val_acc= 0.25000 time= 0.01563
Epoch: 0005 train_loss= 1.38595 train_acc= 0.32227 val_loss= 1.38919 val_acc= 0.25000 time= 0.01563
Epoch: 0006 train_loss= 1.38449 train_acc= 0.32227 val_loss= 1.38882 val_acc= 0.25000 time= 0.02343
Epoch: 0007 train_loss= 1.38406 train_acc= 0.32227 val_loss= 1.38855 val_acc= 0.25000 time= 0.00803
Epoch: 0008 train_loss= 1.38176 train_acc= 0.32227 val_loss= 1.38846 val_acc= 0.25000 time= 0.01563
Epoch: 0009 train_loss= 1.38083 train_acc= 0.32422 val_loss= 1.38849 val_acc= 0.25000 time= 0.01563
Epoch: 0010 train_loss= 1.37937 train_acc= 0.32227 val_loss= 1.38861 val_acc= 0.25000 time= 0.00000
Epoch: 0011 train_loss= 1.37958 train_acc= 0.32031 val_loss= 1.38878 val_acc= 0.25000 time= 0.01563
Epoch: 0012 train_loss= 1.37669 train_acc= 0.32227 val_loss= 1.38908 val_acc= 0.25000 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 1.38674 accuracy= 0.31858 time= 0.00000 
