Epoch: 0001 train_loss= 2.08711 train_acc= 0.13962 val_loss= 2.08454 val_acc= 0.03448 time= 0.40121
Epoch: 0002 train_loss= 2.08474 train_acc= 0.13585 val_loss= 2.08198 val_acc= 0.03448 time= 0.01562
Epoch: 0003 train_loss= 2.08269 train_acc= 0.13585 val_loss= 2.07978 val_acc= 0.03448 time= 0.00000
Epoch: 0004 train_loss= 2.08086 train_acc= 0.13585 val_loss= 2.07788 val_acc= 0.03448 time= 0.01563
Epoch: 0005 train_loss= 2.07879 train_acc= 0.13962 val_loss= 2.07636 val_acc= 0.03448 time= 0.00000
Epoch: 0006 train_loss= 2.07795 train_acc= 0.13585 val_loss= 2.07520 val_acc= 0.03448 time= 0.01563
Epoch: 0007 train_loss= 2.07695 train_acc= 0.13585 val_loss= 2.07439 val_acc= 0.03448 time= 0.00000
Epoch: 0008 train_loss= 2.07546 train_acc= 0.13585 val_loss= 2.07388 val_acc= 0.03448 time= 0.01563
Epoch: 0009 train_loss= 2.07547 train_acc= 0.13585 val_loss= 2.07357 val_acc= 0.03448 time= 0.00000
Epoch: 0010 train_loss= 2.07467 train_acc= 0.13585 val_loss= 2.07343 val_acc= 0.03448 time= 0.00000
Epoch: 0011 train_loss= 2.07404 train_acc= 0.13585 val_loss= 2.07340 val_acc= 0.03448 time= 0.01562
Epoch: 0012 train_loss= 2.07431 train_acc= 0.14340 val_loss= 2.07347 val_acc= 0.03448 time= 0.00000
Epoch: 0013 train_loss= 2.07328 train_acc= 0.13585 val_loss= 2.07359 val_acc= 0.03448 time= 0.01563
Epoch: 0014 train_loss= 2.07289 train_acc= 0.13585 val_loss= 2.07385 val_acc= 0.03448 time= 0.00000
Epoch: 0015 train_loss= 2.07162 train_acc= 0.14717 val_loss= 2.07429 val_acc= 0.03448 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.08341 accuracy= 0.13559 time= 0.00000 
