Epoch: 0001 train_loss= 1.46563 train_acc= 0.24162 val_loss= 1.40165 val_acc= 0.23214 time= 0.65630
Epoch: 0002 train_loss= 1.43891 train_acc= 0.25000 val_loss= 1.39464 val_acc= 0.23214 time= 0.01562
Epoch: 0003 train_loss= 1.39746 train_acc= 0.25000 val_loss= 1.38960 val_acc= 0.23214 time= 0.01563
Epoch: 0004 train_loss= 1.41275 train_acc= 0.24302 val_loss= 1.38513 val_acc= 0.32143 time= 0.01563
Epoch: 0005 train_loss= 1.40534 train_acc= 0.27235 val_loss= 1.38224 val_acc= 0.32143 time= 0.00000
Epoch: 0006 train_loss= 1.39161 train_acc= 0.29190 val_loss= 1.38007 val_acc= 0.32143 time= 0.03125
Epoch: 0007 train_loss= 1.39756 train_acc= 0.29609 val_loss= 1.37862 val_acc= 0.32143 time= 0.00000
Epoch: 0008 train_loss= 1.41272 train_acc= 0.30587 val_loss= 1.37767 val_acc= 0.32143 time= 0.01563
Epoch: 0009 train_loss= 1.40606 train_acc= 0.31006 val_loss= 1.37713 val_acc= 0.32143 time= 0.01563
Epoch: 0010 train_loss= 1.40344 train_acc= 0.30587 val_loss= 1.37713 val_acc= 0.32143 time= 0.01563
Epoch: 0011 train_loss= 1.38998 train_acc= 0.31006 val_loss= 1.37718 val_acc= 0.32143 time= 0.01563
Epoch: 0012 train_loss= 1.38310 train_acc= 0.30168 val_loss= 1.37734 val_acc= 0.32143 time= 0.01563
Epoch: 0013 train_loss= 1.39430 train_acc= 0.30587 val_loss= 1.37774 val_acc= 0.32143 time= 0.01563
Epoch: 0014 train_loss= 1.39365 train_acc= 0.29888 val_loss= 1.37851 val_acc= 0.33929 time= 0.01563
Epoch: 0015 train_loss= 1.39159 train_acc= 0.31145 val_loss= 1.37935 val_acc= 0.33929 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.39608 accuracy= 0.29204 time= 0.00000 
