Epoch: 0001 train_loss= 0.70122 train_acc= 0.44545 val_loss= 0.69832 val_acc= 0.47541 time= 0.24789
Epoch: 0002 train_loss= 0.69820 train_acc= 0.53091 val_loss= 0.69624 val_acc= 0.47541 time= 0.00205
Epoch: 0003 train_loss= 0.69599 train_acc= 0.53636 val_loss= 0.69490 val_acc= 0.47541 time= 0.01563
Epoch: 0004 train_loss= 0.69467 train_acc= 0.53273 val_loss= 0.69412 val_acc= 0.47541 time= 0.00000
Epoch: 0005 train_loss= 0.69377 train_acc= 0.53273 val_loss= 0.69376 val_acc= 0.47541 time= 0.01563
Epoch: 0006 train_loss= 0.69329 train_acc= 0.53273 val_loss= 0.69367 val_acc= 0.47541 time= 0.01563
Epoch: 0007 train_loss= 0.69286 train_acc= 0.53455 val_loss= 0.69375 val_acc= 0.47541 time= 0.01563
Epoch: 0008 train_loss= 0.69291 train_acc= 0.53818 val_loss= 0.69389 val_acc= 0.47541 time= 0.00000
Epoch: 0009 train_loss= 0.69306 train_acc= 0.53273 val_loss= 0.69404 val_acc= 0.47541 time= 0.01563
Epoch: 0010 train_loss= 0.69322 train_acc= 0.53636 val_loss= 0.69415 val_acc= 0.47541 time= 0.01563
Epoch: 0011 train_loss= 0.69294 train_acc= 0.53818 val_loss= 0.69422 val_acc= 0.47541 time= 0.00000
Epoch: 0012 train_loss= 0.69314 train_acc= 0.53818 val_loss= 0.69423 val_acc= 0.47541 time= 0.01563
Epoch: 0013 train_loss= 0.69315 train_acc= 0.54182 val_loss= 0.69417 val_acc= 0.47541 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69152 accuracy= 0.57377 time= 0.00000 
