Epoch: 0001 train_loss= 2.10751 train_acc= 0.12830 val_loss= 2.08001 val_acc= 0.13793 time= 0.17605
Epoch: 0002 train_loss= 2.09484 train_acc= 0.13208 val_loss= 2.07664 val_acc= 0.13793 time= 0.01563
Epoch: 0003 train_loss= 2.09476 train_acc= 0.13208 val_loss= 2.07451 val_acc= 0.10345 time= 0.00000
Epoch: 0004 train_loss= 2.07983 train_acc= 0.14340 val_loss= 2.07344 val_acc= 0.17241 time= 0.01563
Epoch: 0005 train_loss= 2.07745 train_acc= 0.14340 val_loss= 2.07322 val_acc= 0.17241 time= 0.01563
Epoch: 0006 train_loss= 2.06943 train_acc= 0.18868 val_loss= 2.07382 val_acc= 0.17241 time= 0.00000
Epoch: 0007 train_loss= 2.06530 train_acc= 0.15849 val_loss= 2.07485 val_acc= 0.13793 time= 0.01563
Epoch: 0008 train_loss= 2.06266 train_acc= 0.16226 val_loss= 2.07613 val_acc= 0.10345 time= 0.01563
Epoch: 0009 train_loss= 2.06264 train_acc= 0.17358 val_loss= 2.07775 val_acc= 0.06897 time= 0.00000
Epoch: 0010 train_loss= 2.06064 train_acc= 0.17358 val_loss= 2.07977 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.05514 train_acc= 0.19245 val_loss= 2.08172 val_acc= 0.06897 time= 0.01563
Epoch: 0012 train_loss= 2.05715 train_acc= 0.18491 val_loss= 2.08408 val_acc= 0.06897 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08000 accuracy= 0.10169 time= 0.01562 
