Epoch: 0001 train_loss= 1.39294 train_acc= 0.19727 val_loss= 1.39271 val_acc= 0.25000 time= 0.34543
Epoch: 0002 train_loss= 1.39102 train_acc= 0.28906 val_loss= 1.39258 val_acc= 0.25000 time= 0.01563
Epoch: 0003 train_loss= 1.38942 train_acc= 0.29492 val_loss= 1.39260 val_acc= 0.25000 time= 0.01563
Epoch: 0004 train_loss= 1.38781 train_acc= 0.29492 val_loss= 1.39266 val_acc= 0.25000 time= 0.00000
Epoch: 0005 train_loss= 1.38677 train_acc= 0.29492 val_loss= 1.39282 val_acc= 0.25000 time= 0.01562
Epoch: 0006 train_loss= 1.38557 train_acc= 0.29492 val_loss= 1.39309 val_acc= 0.25000 time= 0.01563
Epoch: 0007 train_loss= 1.38508 train_acc= 0.29492 val_loss= 1.39343 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.38368 train_acc= 0.29492 val_loss= 1.39389 val_acc= 0.25000 time= 0.03125
Epoch: 0009 train_loss= 1.38306 train_acc= 0.29492 val_loss= 1.39451 val_acc= 0.25000 time= 0.02247
Epoch: 0010 train_loss= 1.38251 train_acc= 0.29492 val_loss= 1.39522 val_acc= 0.25000 time= 0.02358
Epoch: 0011 train_loss= 1.38155 train_acc= 0.29492 val_loss= 1.39597 val_acc= 0.25000 time= 0.02501
Epoch: 0012 train_loss= 1.38121 train_acc= 0.29492 val_loss= 1.39674 val_acc= 0.25000 time= 0.02201
Early stopping...
Optimization Finished!
Test set results: cost= 1.38565 accuracy= 0.30973 time= 0.00700 
