Epoch: 0001 train_loss= 1.19078 train_acc= 0.51212 val_loss= 0.89258 val_acc= 0.54098 time= 0.09376
Epoch: 0002 train_loss= 0.87796 train_acc= 0.50000 val_loss= 0.79125 val_acc= 0.44262 time= 0.01563
Epoch: 0003 train_loss= 1.01940 train_acc= 0.56667 val_loss= 0.80741 val_acc= 0.45902 time= 0.00000
Epoch: 0004 train_loss= 1.16623 train_acc= 0.51515 val_loss= 0.77629 val_acc= 0.45902 time= 0.01563
Epoch: 0005 train_loss= 1.09738 train_acc= 0.46061 val_loss= 0.75820 val_acc= 0.52459 time= 0.01563
Epoch: 0006 train_loss= 1.15317 train_acc= 0.54545 val_loss= 0.71071 val_acc= 0.49180 time= 0.01563
Epoch: 0007 train_loss= 0.96364 train_acc= 0.52121 val_loss= 0.67474 val_acc= 0.57377 time= 0.01563
Epoch: 0008 train_loss= 1.01506 train_acc= 0.50303 val_loss= 0.66985 val_acc= 0.65574 time= 0.00000
Epoch: 0009 train_loss= 1.03009 train_acc= 0.46667 val_loss= 0.66819 val_acc= 0.62295 time= 0.01563
Epoch: 0010 train_loss= 0.85456 train_acc= 0.46970 val_loss= 0.67081 val_acc= 0.57377 time= 0.01562
Epoch: 0011 train_loss= 1.01236 train_acc= 0.48485 val_loss= 0.68327 val_acc= 0.54098 time= 0.01563
Epoch: 0012 train_loss= 0.85618 train_acc= 0.51818 val_loss= 0.71715 val_acc= 0.50820 time= 0.00000
Epoch: 0013 train_loss= 0.77471 train_acc= 0.49697 val_loss= 0.75236 val_acc= 0.50820 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.73211 accuracy= 0.48361 time= 0.01563 
