Epoch: 0001 train_loss= 1.39510 train_acc= 0.24721 val_loss= 1.39921 val_acc= 0.19643 time= 0.78130
Epoch: 0002 train_loss= 1.39126 train_acc= 0.25000 val_loss= 1.39569 val_acc= 0.19643 time= 0.00000
Epoch: 0003 train_loss= 1.38898 train_acc= 0.25698 val_loss= 1.39275 val_acc= 0.17857 time= 0.01562
Epoch: 0004 train_loss= 1.38659 train_acc= 0.20950 val_loss= 1.39045 val_acc= 0.26786 time= 0.00000
Epoch: 0005 train_loss= 1.38361 train_acc= 0.32123 val_loss= 1.38869 val_acc= 0.28571 time= 0.01563
Epoch: 0006 train_loss= 1.38169 train_acc= 0.31006 val_loss= 1.38751 val_acc= 0.28571 time= 0.00000
Epoch: 0007 train_loss= 1.38039 train_acc= 0.30726 val_loss= 1.38676 val_acc= 0.28571 time= 0.01563
Epoch: 0008 train_loss= 1.37925 train_acc= 0.30866 val_loss= 1.38639 val_acc= 0.28571 time= 0.00000
Epoch: 0009 train_loss= 1.37714 train_acc= 0.30726 val_loss= 1.38634 val_acc= 0.28571 time= 0.00000
Epoch: 0010 train_loss= 1.37696 train_acc= 0.30726 val_loss= 1.38663 val_acc= 0.28571 time= 0.01563
Epoch: 0011 train_loss= 1.37718 train_acc= 0.30726 val_loss= 1.38726 val_acc= 0.28571 time= 0.00000
Epoch: 0012 train_loss= 1.37617 train_acc= 0.30866 val_loss= 1.38812 val_acc= 0.28571 time= 0.01563
Epoch: 0013 train_loss= 1.37549 train_acc= 0.30726 val_loss= 1.38919 val_acc= 0.28571 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.37215 accuracy= 0.29204 time= 0.00000 
