Epoch: 0001 train_loss= 2.08897 train_acc= 0.11051 val_loss= 2.09280 val_acc= 0.13793 time= 0.87832
Epoch: 0002 train_loss= 2.08570 train_acc= 0.11051 val_loss= 2.09333 val_acc= 0.13793 time= 0.00000
Epoch: 0003 train_loss= 2.08293 train_acc= 0.11051 val_loss= 2.09388 val_acc= 0.13793 time= 0.01563
Epoch: 0004 train_loss= 2.08134 train_acc= 0.11321 val_loss= 2.09439 val_acc= 0.13793 time= 0.00000
Epoch: 0005 train_loss= 2.08106 train_acc= 0.10782 val_loss= 2.09504 val_acc= 0.10345 time= 0.00000
Epoch: 0006 train_loss= 2.07852 train_acc= 0.11590 val_loss= 2.09571 val_acc= 0.10345 time= 0.01563
Epoch: 0007 train_loss= 2.07535 train_acc= 0.14016 val_loss= 2.09635 val_acc= 0.03448 time= 0.00000
Epoch: 0008 train_loss= 2.07594 train_acc= 0.15094 val_loss= 2.09713 val_acc= 0.03448 time= 0.00000
Epoch: 0009 train_loss= 2.07229 train_acc= 0.17251 val_loss= 2.09797 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.07279 train_acc= 0.15364 val_loss= 2.09885 val_acc= 0.06897 time= 0.00000
Epoch: 0011 train_loss= 2.06961 train_acc= 0.15633 val_loss= 2.09982 val_acc= 0.06897 time= 0.00000
Epoch: 0012 train_loss= 2.07012 train_acc= 0.13747 val_loss= 2.10097 val_acc= 0.10345 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.08284 accuracy= 0.15254 time= 0.00000 
