Epoch: 0001 train_loss= 0.99775 train_acc= 0.49091 val_loss= 0.81588 val_acc= 0.49180 time= 0.62428
Epoch: 0002 train_loss= 1.29504 train_acc= 0.52909 val_loss= 1.29221 val_acc= 0.47541 time= 0.02201
Epoch: 0003 train_loss= 1.90103 train_acc= 0.48000 val_loss= 1.30860 val_acc= 0.47541 time= 0.02100
Epoch: 0004 train_loss= 2.49471 train_acc= 0.48182 val_loss= 0.96672 val_acc= 0.47541 time= 0.02100
Epoch: 0005 train_loss= 0.88953 train_acc= 0.52000 val_loss= 0.73845 val_acc= 0.47541 time= 0.02201
Epoch: 0006 train_loss= 0.90455 train_acc= 0.49273 val_loss= 0.77181 val_acc= 0.54098 time= 0.02100
Epoch: 0007 train_loss= 1.45051 train_acc= 0.49455 val_loss= 0.80676 val_acc= 0.54098 time= 0.02100
Epoch: 0008 train_loss= 1.23909 train_acc= 0.55091 val_loss= 0.75605 val_acc= 0.57377 time= 0.02100
Epoch: 0009 train_loss= 2.33054 train_acc= 0.54364 val_loss= 0.72447 val_acc= 0.47541 time= 0.02000
Epoch: 0010 train_loss= 1.02056 train_acc= 0.51273 val_loss= 0.74719 val_acc= 0.49180 time= 0.02200
Epoch: 0011 train_loss= 0.93387 train_acc= 0.53636 val_loss= 0.81706 val_acc= 0.49180 time= 0.01063
Epoch: 0012 train_loss= 0.93855 train_acc= 0.49091 val_loss= 0.83583 val_acc= 0.49180 time= 0.03125
Epoch: 0013 train_loss= 1.22833 train_acc= 0.53636 val_loss= 0.92530 val_acc= 0.49180 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.75468 accuracy= 0.46721 time= 0.00000 
