Epoch: 0001 train_loss= 2.13410 train_acc= 0.10063 val_loss= 2.09327 val_acc= 0.10345 time= 0.09376
Epoch: 0002 train_loss= 2.11414 train_acc= 0.10063 val_loss= 2.09013 val_acc= 0.17241 time= 0.00000
Epoch: 0003 train_loss= 2.10599 train_acc= 0.09434 val_loss= 2.08785 val_acc= 0.10345 time= 0.01562
Epoch: 0004 train_loss= 2.09469 train_acc= 0.16352 val_loss= 2.08643 val_acc= 0.06897 time= 0.01563
Epoch: 0005 train_loss= 2.10200 train_acc= 0.16981 val_loss= 2.08559 val_acc= 0.06897 time= 0.00000
Epoch: 0006 train_loss= 2.08829 train_acc= 0.11950 val_loss= 2.08527 val_acc= 0.03448 time= 0.01563
Epoch: 0007 train_loss= 2.06912 train_acc= 0.13836 val_loss= 2.08529 val_acc= 0.03448 time= 0.00000
Epoch: 0008 train_loss= 2.07054 train_acc= 0.15723 val_loss= 2.08553 val_acc= 0.03448 time= 0.01563
Epoch: 0009 train_loss= 2.06667 train_acc= 0.15094 val_loss= 2.08608 val_acc= 0.03448 time= 0.00000
Epoch: 0010 train_loss= 2.06110 train_acc= 0.13208 val_loss= 2.08690 val_acc= 0.03448 time= 0.01563
Epoch: 0011 train_loss= 2.07094 train_acc= 0.13836 val_loss= 2.08769 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.06776 train_acc= 0.16352 val_loss= 2.08866 val_acc= 0.03448 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.05506 accuracy= 0.16949 time= 0.00000 
