Epoch: 0001 train_loss= 0.70093 train_acc= 0.55091 val_loss= 0.69822 val_acc= 0.47541 time= 0.46878
Epoch: 0002 train_loss= 0.69751 train_acc= 0.53273 val_loss= 0.69644 val_acc= 0.49180 time= 0.00000
Epoch: 0003 train_loss= 0.69484 train_acc= 0.53636 val_loss= 0.69542 val_acc= 0.49180 time= 0.01563
Epoch: 0004 train_loss= 0.69302 train_acc= 0.53455 val_loss= 0.69499 val_acc= 0.49180 time= 0.00000
Epoch: 0005 train_loss= 0.69115 train_acc= 0.53455 val_loss= 0.69497 val_acc= 0.49180 time= 0.01562
Epoch: 0006 train_loss= 0.69056 train_acc= 0.53455 val_loss= 0.69524 val_acc= 0.49180 time= 0.00000
Epoch: 0007 train_loss= 0.68953 train_acc= 0.53818 val_loss= 0.69560 val_acc= 0.49180 time= 0.01563
Epoch: 0008 train_loss= 0.68809 train_acc= 0.54000 val_loss= 0.69595 val_acc= 0.49180 time= 0.01563
Epoch: 0009 train_loss= 0.68716 train_acc= 0.54182 val_loss= 0.69630 val_acc= 0.49180 time= 0.00000
Epoch: 0010 train_loss= 0.68723 train_acc= 0.54182 val_loss= 0.69658 val_acc= 0.49180 time= 0.01563
Epoch: 0011 train_loss= 0.68721 train_acc= 0.54364 val_loss= 0.69652 val_acc= 0.50820 time= 0.00000
Epoch: 0012 train_loss= 0.68649 train_acc= 0.54364 val_loss= 0.69626 val_acc= 0.50820 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69287 accuracy= 0.53279 time= 0.00000 
