Epoch: 0001 train_loss= 1.38218 train_acc= 0.32248 val_loss= 1.38428 val_acc= 0.23214 time= 0.25002
Epoch: 0002 train_loss= 1.37954 train_acc= 0.31596 val_loss= 1.38529 val_acc= 0.23214 time= 0.00000
Epoch: 0003 train_loss= 1.37881 train_acc= 0.31596 val_loss= 1.38653 val_acc= 0.23214 time= 0.01563
Epoch: 0004 train_loss= 1.37520 train_acc= 0.31922 val_loss= 1.38802 val_acc= 0.23214 time= 0.00000
Epoch: 0005 train_loss= 1.37731 train_acc= 0.31596 val_loss= 1.38967 val_acc= 0.23214 time= 0.00000
Epoch: 0006 train_loss= 1.37664 train_acc= 0.31596 val_loss= 1.39144 val_acc= 0.23214 time= 0.01563
Epoch: 0007 train_loss= 1.37646 train_acc= 0.31596 val_loss= 1.39342 val_acc= 0.23214 time= 0.00000
Epoch: 0008 train_loss= 1.37440 train_acc= 0.31596 val_loss= 1.39555 val_acc= 0.23214 time= 0.01563
Epoch: 0009 train_loss= 1.37528 train_acc= 0.31596 val_loss= 1.39775 val_acc= 0.23214 time= 0.00000
Epoch: 0010 train_loss= 1.37416 train_acc= 0.31596 val_loss= 1.40005 val_acc= 0.23214 time= 0.00000
Epoch: 0011 train_loss= 1.37482 train_acc= 0.31596 val_loss= 1.40239 val_acc= 0.23214 time= 0.01563
Epoch: 0012 train_loss= 1.37241 train_acc= 0.31596 val_loss= 1.40477 val_acc= 0.23214 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.37917 accuracy= 0.29204 time= 0.00000 
