Epoch: 0001 train_loss= 1.39207 train_acc= 0.26367 val_loss= 1.39051 val_acc= 0.26786 time= 0.39403
Epoch: 0002 train_loss= 1.39029 train_acc= 0.26758 val_loss= 1.39032 val_acc= 0.26786 time= 0.01920
Epoch: 0003 train_loss= 1.38859 train_acc= 0.26758 val_loss= 1.39008 val_acc= 0.26786 time= 0.02000
Epoch: 0004 train_loss= 1.38717 train_acc= 0.28125 val_loss= 1.38973 val_acc= 0.26786 time= 0.01945
Epoch: 0005 train_loss= 1.38603 train_acc= 0.28320 val_loss= 1.38950 val_acc= 0.26786 time= 0.02016
Epoch: 0006 train_loss= 1.38459 train_acc= 0.29688 val_loss= 1.38941 val_acc= 0.26786 time= 0.01935
Epoch: 0007 train_loss= 1.38352 train_acc= 0.29297 val_loss= 1.38949 val_acc= 0.21429 time= 0.01517
Epoch: 0008 train_loss= 1.38168 train_acc= 0.25977 val_loss= 1.38976 val_acc= 0.21429 time= 0.01609
Epoch: 0009 train_loss= 1.38118 train_acc= 0.28711 val_loss= 1.39023 val_acc= 0.21429 time= 0.01511
Epoch: 0010 train_loss= 1.37934 train_acc= 0.32422 val_loss= 1.39093 val_acc= 0.21429 time= 0.01519
Epoch: 0011 train_loss= 1.37823 train_acc= 0.31250 val_loss= 1.39186 val_acc= 0.21429 time= 0.01852
Epoch: 0012 train_loss= 1.37692 train_acc= 0.31250 val_loss= 1.39307 val_acc= 0.21429 time= 0.01700
Early stopping...
Optimization Finished!
Test set results: cost= 1.37791 accuracy= 0.29204 time= 0.00600 
