Epoch: 0001 train_loss= 2.07796 train_acc= 0.16352 val_loss= 2.07075 val_acc= 0.13793 time= 0.07857
Epoch: 0002 train_loss= 2.07408 train_acc= 0.13836 val_loss= 2.07241 val_acc= 0.13793 time= 0.00000
Epoch: 0003 train_loss= 2.06884 train_acc= 0.16981 val_loss= 2.07353 val_acc= 0.13793 time= 0.02241
Epoch: 0004 train_loss= 2.05705 train_acc= 0.17610 val_loss= 2.07549 val_acc= 0.13793 time= 0.00706
Epoch: 0005 train_loss= 2.05220 train_acc= 0.16981 val_loss= 2.07792 val_acc= 0.13793 time= 0.00000
Epoch: 0006 train_loss= 2.05015 train_acc= 0.16981 val_loss= 2.08083 val_acc= 0.13793 time= 0.01563
Epoch: 0007 train_loss= 2.04348 train_acc= 0.18239 val_loss= 2.08453 val_acc= 0.13793 time= 0.00000
Epoch: 0008 train_loss= 2.03102 train_acc= 0.18239 val_loss= 2.08838 val_acc= 0.17241 time= 0.01563
Epoch: 0009 train_loss= 2.03975 train_acc= 0.15094 val_loss= 2.09243 val_acc= 0.17241 time= 0.01563
Epoch: 0010 train_loss= 2.03882 train_acc= 0.18868 val_loss= 2.09684 val_acc= 0.17241 time= 0.00000
Epoch: 0011 train_loss= 2.03455 train_acc= 0.18239 val_loss= 2.10167 val_acc= 0.17241 time= 0.01563
Epoch: 0012 train_loss= 2.02848 train_acc= 0.16981 val_loss= 2.10726 val_acc= 0.17241 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.09273 accuracy= 0.08475 time= 0.00000 
