Epoch: 0001 train_loss= 2.11751 train_acc= 0.10782 val_loss= 2.10084 val_acc= 0.06897 time= 0.62315
Epoch: 0002 train_loss= 2.10979 train_acc= 0.10782 val_loss= 2.09721 val_acc= 0.03448 time= 0.01100
Epoch: 0003 train_loss= 2.09332 train_acc= 0.12668 val_loss= 2.09369 val_acc= 0.03448 time= 0.01000
Epoch: 0004 train_loss= 2.09339 train_acc= 0.12668 val_loss= 2.09087 val_acc= 0.06897 time= 0.00800
Epoch: 0005 train_loss= 2.08275 train_acc= 0.14016 val_loss= 2.08938 val_acc= 0.10345 time= 0.00800
Epoch: 0006 train_loss= 2.07767 train_acc= 0.11860 val_loss= 2.08847 val_acc= 0.13793 time= 0.00800
Epoch: 0007 train_loss= 2.08074 train_acc= 0.14016 val_loss= 2.08832 val_acc= 0.13793 time= 0.00900
Epoch: 0008 train_loss= 2.08821 train_acc= 0.12399 val_loss= 2.08885 val_acc= 0.03448 time= 0.00900
Epoch: 0009 train_loss= 2.06916 train_acc= 0.14286 val_loss= 2.08930 val_acc= 0.06897 time= 0.01000
Epoch: 0010 train_loss= 2.07152 train_acc= 0.14555 val_loss= 2.09010 val_acc= 0.10345 time= 0.01000
Epoch: 0011 train_loss= 2.06349 train_acc= 0.15903 val_loss= 2.09100 val_acc= 0.10345 time= 0.00900
Epoch: 0012 train_loss= 2.06880 train_acc= 0.17251 val_loss= 2.09206 val_acc= 0.06897 time= 0.00800
Early stopping...
Optimization Finished!
Test set results: cost= 2.06192 accuracy= 0.11864 time= 0.00400 
