Epoch: 0001 train_loss= 0.70114 train_acc= 0.48571 val_loss= 0.69835 val_acc= 0.50820 time= 0.37777
Epoch: 0002 train_loss= 0.69819 train_acc= 0.52208 val_loss= 0.69643 val_acc= 0.49180 time= 0.00000
Epoch: 0003 train_loss= 0.69602 train_acc= 0.51429 val_loss= 0.69527 val_acc= 0.49180 time= 0.01563
Epoch: 0004 train_loss= 0.69459 train_acc= 0.51299 val_loss= 0.69466 val_acc= 0.49180 time= 0.01562
Epoch: 0005 train_loss= 0.69362 train_acc= 0.51429 val_loss= 0.69445 val_acc= 0.49180 time= 0.00000
Epoch: 0006 train_loss= 0.69315 train_acc= 0.51299 val_loss= 0.69451 val_acc= 0.49180 time= 0.01563
Epoch: 0007 train_loss= 0.69290 train_acc= 0.51169 val_loss= 0.69473 val_acc= 0.49180 time= 0.01563
Epoch: 0008 train_loss= 0.69280 train_acc= 0.51039 val_loss= 0.69501 val_acc= 0.49180 time= 0.01563
Epoch: 0009 train_loss= 0.69301 train_acc= 0.51299 val_loss= 0.69522 val_acc= 0.49180 time= 0.00000
Epoch: 0010 train_loss= 0.69274 train_acc= 0.51818 val_loss= 0.69531 val_acc= 0.49180 time= 0.01563
Epoch: 0011 train_loss= 0.69300 train_acc= 0.51299 val_loss= 0.69534 val_acc= 0.49180 time= 0.01563
Epoch: 0012 train_loss= 0.69279 train_acc= 0.51818 val_loss= 0.69525 val_acc= 0.50820 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69145 accuracy= 0.54918 time= 0.00000 
