Epoch: 0001 train_loss= 2.12679 train_acc= 0.09434 val_loss= 2.11971 val_acc= 0.10345 time= 0.95027
Epoch: 0002 train_loss= 2.08449 train_acc= 0.13208 val_loss= 2.12088 val_acc= 0.06897 time= 0.01489
Epoch: 0003 train_loss= 2.11780 train_acc= 0.12938 val_loss= 2.11651 val_acc= 0.03448 time= 0.01563
Epoch: 0004 train_loss= 2.08166 train_acc= 0.13747 val_loss= 2.11686 val_acc= 0.06897 time= 0.01563
Epoch: 0005 train_loss= 2.08316 train_acc= 0.12668 val_loss= 2.12195 val_acc= 0.06897 time= 0.01563
Epoch: 0006 train_loss= 2.06747 train_acc= 0.15364 val_loss= 2.12701 val_acc= 0.06897 time= 0.01945
Epoch: 0007 train_loss= 2.06097 train_acc= 0.18329 val_loss= 2.12958 val_acc= 0.06897 time= 0.01201
Epoch: 0008 train_loss= 2.05588 train_acc= 0.17520 val_loss= 2.13215 val_acc= 0.06897 time= 0.00000
Epoch: 0009 train_loss= 2.06774 train_acc= 0.13477 val_loss= 2.13554 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.05813 train_acc= 0.15364 val_loss= 2.13930 val_acc= 0.06897 time= 0.01562
Epoch: 0011 train_loss= 2.05877 train_acc= 0.15094 val_loss= 2.14206 val_acc= 0.06897 time= 0.01563
Epoch: 0012 train_loss= 2.06758 train_acc= 0.14825 val_loss= 2.14221 val_acc= 0.06897 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.03145 accuracy= 0.15254 time= 0.00000 
