Epoch: 0001 train_loss= 1.38685 train_acc= 0.25279 val_loss= 1.38827 val_acc= 0.21429 time= 0.85943
Epoch: 0002 train_loss= 1.38495 train_acc= 0.25279 val_loss= 1.38726 val_acc= 0.21429 time= 0.01563
Epoch: 0003 train_loss= 1.38254 train_acc= 0.26816 val_loss= 1.38632 val_acc= 0.23214 time= 0.00000
Epoch: 0004 train_loss= 1.38046 train_acc= 0.24581 val_loss= 1.38542 val_acc= 0.35714 time= 0.01562
Epoch: 0005 train_loss= 1.37971 train_acc= 0.31145 val_loss= 1.38459 val_acc= 0.33929 time= 0.00000
Epoch: 0006 train_loss= 1.37634 train_acc= 0.32821 val_loss= 1.38386 val_acc= 0.33929 time= 0.01562
Epoch: 0007 train_loss= 1.37631 train_acc= 0.31983 val_loss= 1.38327 val_acc= 0.33929 time= 0.00000
Epoch: 0008 train_loss= 1.37349 train_acc= 0.33101 val_loss= 1.38274 val_acc= 0.33929 time= 0.01563
Epoch: 0009 train_loss= 1.37475 train_acc= 0.32402 val_loss= 1.38225 val_acc= 0.33929 time= 0.00000
Epoch: 0010 train_loss= 1.37146 train_acc= 0.32542 val_loss= 1.38193 val_acc= 0.33929 time= 0.01563
Epoch: 0011 train_loss= 1.36987 train_acc= 0.32402 val_loss= 1.38180 val_acc= 0.33929 time= 0.00000
Epoch: 0012 train_loss= 1.36897 train_acc= 0.32402 val_loss= 1.38185 val_acc= 0.33929 time= 0.01562
Epoch: 0013 train_loss= 1.36865 train_acc= 0.32402 val_loss= 1.38205 val_acc= 0.33929 time= 0.00000
Epoch: 0014 train_loss= 1.36625 train_acc= 0.32402 val_loss= 1.38240 val_acc= 0.33929 time= 0.01563
Epoch: 0015 train_loss= 1.36794 train_acc= 0.32402 val_loss= 1.38289 val_acc= 0.33929 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.37647 accuracy= 0.30088 time= 0.00000 
