Epoch: 0001 train_loss= 1.46381 train_acc= 0.49351 val_loss= 0.72196 val_acc= 0.40984 time= 1.03163
Epoch: 0002 train_loss= 0.96365 train_acc= 0.49481 val_loss= 0.72037 val_acc= 0.47541 time= 0.01563
Epoch: 0003 train_loss= 1.49357 train_acc= 0.51169 val_loss= 0.70915 val_acc= 0.40984 time= 0.03125
Epoch: 0004 train_loss= 1.04782 train_acc= 0.48701 val_loss= 0.70830 val_acc= 0.47541 time= 0.03125
Epoch: 0005 train_loss= 1.05697 train_acc= 0.50390 val_loss= 0.70800 val_acc= 0.42623 time= 0.01562
Epoch: 0006 train_loss= 1.00771 train_acc= 0.50649 val_loss= 0.70214 val_acc= 0.47541 time= 0.03125
Epoch: 0007 train_loss= 1.25854 train_acc= 0.49870 val_loss= 0.71240 val_acc= 0.57377 time= 0.01562
Epoch: 0008 train_loss= 0.83323 train_acc= 0.50649 val_loss= 0.73232 val_acc= 0.57377 time= 0.03125
Epoch: 0009 train_loss= 0.89404 train_acc= 0.50909 val_loss= 0.73867 val_acc= 0.62295 time= 0.03125
Epoch: 0010 train_loss= 0.95583 train_acc= 0.49481 val_loss= 0.72543 val_acc= 0.62295 time= 0.01563
Epoch: 0011 train_loss= 1.03503 train_acc= 0.48961 val_loss= 0.72601 val_acc= 0.63934 time= 0.03125
Epoch: 0012 train_loss= 1.02400 train_acc= 0.50000 val_loss= 0.74566 val_acc= 0.59016 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.70814 accuracy= 0.48361 time= 0.01563 
