Epoch: 0001 train_loss= 2.08732 train_acc= 0.15094 val_loss= 2.08583 val_acc= 0.10345 time= 0.75042
Epoch: 0002 train_loss= 2.08469 train_acc= 0.18059 val_loss= 2.08468 val_acc= 0.06897 time= 0.00000
Epoch: 0003 train_loss= 2.08245 train_acc= 0.18059 val_loss= 2.08378 val_acc= 0.06897 time= 0.01562
Epoch: 0004 train_loss= 2.08008 train_acc= 0.18059 val_loss= 2.08329 val_acc= 0.06897 time= 0.00000
Epoch: 0005 train_loss= 2.07820 train_acc= 0.17520 val_loss= 2.08322 val_acc= 0.06897 time= 0.01563
Epoch: 0006 train_loss= 2.07617 train_acc= 0.18329 val_loss= 2.08361 val_acc= 0.06897 time= 0.01563
Epoch: 0007 train_loss= 2.07507 train_acc= 0.18059 val_loss= 2.08447 val_acc= 0.06897 time= 0.00000
Epoch: 0008 train_loss= 2.07264 train_acc= 0.17251 val_loss= 2.08576 val_acc= 0.06897 time= 0.01563
Epoch: 0009 train_loss= 2.07139 train_acc= 0.18059 val_loss= 2.08739 val_acc= 0.06897 time= 0.00000
Epoch: 0010 train_loss= 2.07007 train_acc= 0.18329 val_loss= 2.08947 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.06890 train_acc= 0.17520 val_loss= 2.09184 val_acc= 0.06897 time= 0.00000
Epoch: 0012 train_loss= 2.06711 train_acc= 0.17790 val_loss= 2.09454 val_acc= 0.06897 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.10286 accuracy= 0.08475 time= 0.00000 
