Epoch: 0001 train_loss= 1.76279 train_acc= 0.47273 val_loss= 0.95875 val_acc= 0.52459 time= 0.17189
Epoch: 0002 train_loss= 2.51261 train_acc= 0.47636 val_loss= 0.78678 val_acc= 0.52459 time= 0.01562
Epoch: 0003 train_loss= 0.85783 train_acc= 0.49636 val_loss= 0.71211 val_acc= 0.50820 time= 0.01563
Epoch: 0004 train_loss= 1.70771 train_acc= 0.48000 val_loss= 0.70674 val_acc= 0.50820 time= 0.01563
Epoch: 0005 train_loss= 0.85005 train_acc= 0.49455 val_loss= 0.75284 val_acc= 0.45902 time= 0.01563
Epoch: 0006 train_loss= 0.78457 train_acc= 0.50364 val_loss= 0.81358 val_acc= 0.49180 time= 0.00000
Epoch: 0007 train_loss= 0.80717 train_acc= 0.52909 val_loss= 0.86695 val_acc= 0.50820 time= 0.01563
Epoch: 0008 train_loss= 0.83267 train_acc= 0.51273 val_loss= 0.90493 val_acc= 0.50820 time= 0.01563
Epoch: 0009 train_loss= 0.76096 train_acc= 0.50182 val_loss= 0.94091 val_acc= 0.50820 time= 0.01563
Epoch: 0010 train_loss= 0.85577 train_acc= 0.47636 val_loss= 0.99308 val_acc= 0.47541 time= 0.01563
Epoch: 0011 train_loss= 0.89159 train_acc= 0.51636 val_loss= 1.01434 val_acc= 0.47541 time= 0.01563
Epoch: 0012 train_loss= 0.88061 train_acc= 0.55091 val_loss= 1.02143 val_acc= 0.47541 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.93948 accuracy= 0.47541 time= 0.00000 
