Epoch: 0001 train_loss= 1.39040 train_acc= 0.29297 val_loss= 1.37230 val_acc= 0.32143 time= 0.53128
Epoch: 0002 train_loss= 1.38847 train_acc= 0.31641 val_loss= 1.37415 val_acc= 0.32143 time= 0.00000
Epoch: 0003 train_loss= 1.38518 train_acc= 0.31250 val_loss= 1.37618 val_acc= 0.32143 time= 0.01562
Epoch: 0004 train_loss= 1.38382 train_acc= 0.31445 val_loss= 1.37838 val_acc= 0.32143 time= 0.00000
Epoch: 0005 train_loss= 1.38131 train_acc= 0.31445 val_loss= 1.38081 val_acc= 0.32143 time= 0.00000
Epoch: 0006 train_loss= 1.37853 train_acc= 0.31641 val_loss= 1.38344 val_acc= 0.32143 time= 0.01563
Epoch: 0007 train_loss= 1.37569 train_acc= 0.31641 val_loss= 1.38627 val_acc= 0.32143 time= 0.00000
Epoch: 0008 train_loss= 1.37372 train_acc= 0.31836 val_loss= 1.38928 val_acc= 0.32143 time= 0.01563
Epoch: 0009 train_loss= 1.37157 train_acc= 0.31641 val_loss= 1.39249 val_acc= 0.32143 time= 0.00000
Epoch: 0010 train_loss= 1.36930 train_acc= 0.31641 val_loss= 1.39583 val_acc= 0.32143 time= 0.01563
Epoch: 0011 train_loss= 1.36899 train_acc= 0.31641 val_loss= 1.39935 val_acc= 0.32143 time= 0.00000
Epoch: 0012 train_loss= 1.36859 train_acc= 0.31836 val_loss= 1.40300 val_acc= 0.32143 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38357 accuracy= 0.31858 time= 0.00000 
