Epoch: 0001 train_loss= 1.37994 train_acc= 0.31596 val_loss= 1.35447 val_acc= 0.32143 time= 0.22654
Epoch: 0002 train_loss= 1.38022 train_acc= 0.31922 val_loss= 1.35198 val_acc= 0.32143 time= 0.00800
Epoch: 0003 train_loss= 1.37846 train_acc= 0.31922 val_loss= 1.34954 val_acc= 0.32143 time= 0.00700
Epoch: 0004 train_loss= 1.37806 train_acc= 0.31922 val_loss= 1.34717 val_acc= 0.32143 time= 0.00700
Epoch: 0005 train_loss= 1.37505 train_acc= 0.31922 val_loss= 1.34461 val_acc= 0.32143 time= 0.00700
Epoch: 0006 train_loss= 1.37548 train_acc= 0.31922 val_loss= 1.34305 val_acc= 0.32143 time= 0.00800
Epoch: 0007 train_loss= 1.37429 train_acc= 0.31922 val_loss= 1.34156 val_acc= 0.32143 time= 0.00749
Epoch: 0008 train_loss= 1.37346 train_acc= 0.31922 val_loss= 1.34053 val_acc= 0.32143 time= 0.00707
Epoch: 0009 train_loss= 1.37250 train_acc= 0.31922 val_loss= 1.33997 val_acc= 0.32143 time= 0.00804
Epoch: 0010 train_loss= 1.37337 train_acc= 0.31922 val_loss= 1.33989 val_acc= 0.32143 time= 0.00816
Epoch: 0011 train_loss= 1.37323 train_acc= 0.31922 val_loss= 1.33995 val_acc= 0.32143 time= 0.00812
Epoch: 0012 train_loss= 1.37422 train_acc= 0.31922 val_loss= 1.34061 val_acc= 0.32143 time= 0.00800
Epoch: 0013 train_loss= 1.37507 train_acc= 0.31922 val_loss= 1.34144 val_acc= 0.32143 time= 0.00683
Epoch: 0014 train_loss= 1.37298 train_acc= 0.31922 val_loss= 1.34238 val_acc= 0.32143 time= 0.00909
Early stopping...
Optimization Finished!
Test set results: cost= 1.38824 accuracy= 0.31858 time= 0.00400 
