Epoch: 0001 train_loss= 2.10558 train_acc= 0.09164 val_loss= 2.07726 val_acc= 0.10345 time= 0.92971
Epoch: 0002 train_loss= 2.08373 train_acc= 0.13747 val_loss= 2.07238 val_acc= 0.13793 time= 0.01500
Epoch: 0003 train_loss= 2.06648 train_acc= 0.17790 val_loss= 2.07176 val_acc= 0.13793 time= 0.01400
Epoch: 0004 train_loss= 2.07635 train_acc= 0.17251 val_loss= 2.07249 val_acc= 0.13793 time= 0.01300
Epoch: 0005 train_loss= 2.06068 train_acc= 0.18868 val_loss= 2.07415 val_acc= 0.13793 time= 0.01400
Epoch: 0006 train_loss= 2.06187 train_acc= 0.16173 val_loss= 2.07631 val_acc= 0.17241 time= 0.01600
Epoch: 0007 train_loss= 2.05705 train_acc= 0.18868 val_loss= 2.07827 val_acc= 0.17241 time= 0.01800
Epoch: 0008 train_loss= 2.05026 train_acc= 0.19137 val_loss= 2.07977 val_acc= 0.17241 time= 0.01900
Epoch: 0009 train_loss= 2.04731 train_acc= 0.17251 val_loss= 2.08132 val_acc= 0.17241 time= 0.01600
Epoch: 0010 train_loss= 2.05477 train_acc= 0.16712 val_loss= 2.08074 val_acc= 0.13793 time= 0.01700
Epoch: 0011 train_loss= 2.05165 train_acc= 0.19137 val_loss= 2.07867 val_acc= 0.10345 time= 0.01500
Epoch: 0012 train_loss= 2.04217 train_acc= 0.19137 val_loss= 2.07727 val_acc= 0.10345 time= 0.01500
Early stopping...
Optimization Finished!
Test set results: cost= 2.09349 accuracy= 0.08475 time= 0.00800 
