Epoch: 0001 train_loss= 1.46728 train_acc= 0.21508 val_loss= 1.40165 val_acc= 0.23214 time= 0.71885
Epoch: 0002 train_loss= 1.48946 train_acc= 0.18715 val_loss= 1.40221 val_acc= 0.21429 time= 0.01563
Epoch: 0003 train_loss= 1.44674 train_acc= 0.22067 val_loss= 1.40346 val_acc= 0.17857 time= 0.01563
Epoch: 0004 train_loss= 1.43997 train_acc= 0.22346 val_loss= 1.40368 val_acc= 0.17857 time= 0.00000
Epoch: 0005 train_loss= 1.43068 train_acc= 0.27933 val_loss= 1.40331 val_acc= 0.23214 time= 0.03125
Epoch: 0006 train_loss= 1.42821 train_acc= 0.25838 val_loss= 1.40287 val_acc= 0.26786 time= 0.01563
Epoch: 0007 train_loss= 1.40383 train_acc= 0.22905 val_loss= 1.40170 val_acc= 0.25000 time= 0.00000
Epoch: 0008 train_loss= 1.41044 train_acc= 0.21648 val_loss= 1.40057 val_acc= 0.25000 time= 0.01563
Epoch: 0009 train_loss= 1.39537 train_acc= 0.26536 val_loss= 1.40027 val_acc= 0.23214 time= 0.01563
Epoch: 0010 train_loss= 1.39058 train_acc= 0.28631 val_loss= 1.40073 val_acc= 0.25000 time= 0.01563
Epoch: 0011 train_loss= 1.39039 train_acc= 0.26676 val_loss= 1.40188 val_acc= 0.28571 time= 0.01563
Epoch: 0012 train_loss= 1.37904 train_acc= 0.32542 val_loss= 1.40358 val_acc= 0.32143 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.40644 accuracy= 0.25664 time= 0.00000 
