Epoch: 0001 train_loss= 1.38316 train_acc= 0.29749 val_loss= 1.38688 val_acc= 0.25000 time= 0.92211
Epoch: 0002 train_loss= 1.38235 train_acc= 0.29749 val_loss= 1.38614 val_acc= 0.23333 time= 0.01563
Epoch: 0003 train_loss= 1.38122 train_acc= 0.31983 val_loss= 1.38549 val_acc= 0.23333 time= 0.00000
Epoch: 0004 train_loss= 1.38073 train_acc= 0.31145 val_loss= 1.38488 val_acc= 0.23333 time= 0.01563
Epoch: 0005 train_loss= 1.37985 train_acc= 0.31425 val_loss= 1.38430 val_acc= 0.23333 time= 0.00000
Epoch: 0006 train_loss= 1.37855 train_acc= 0.31285 val_loss= 1.38378 val_acc= 0.23333 time= 0.01563
Epoch: 0007 train_loss= 1.37748 train_acc= 0.31285 val_loss= 1.38334 val_acc= 0.23333 time= 0.00000
Epoch: 0008 train_loss= 1.37739 train_acc= 0.31564 val_loss= 1.38295 val_acc= 0.23333 time= 0.01563
Epoch: 0009 train_loss= 1.37612 train_acc= 0.31564 val_loss= 1.38265 val_acc= 0.23333 time= 0.00000
Epoch: 0010 train_loss= 1.37685 train_acc= 0.31285 val_loss= 1.38239 val_acc= 0.23333 time= 0.01563
Epoch: 0011 train_loss= 1.37552 train_acc= 0.31425 val_loss= 1.38219 val_acc= 0.23333 time= 0.00000
Epoch: 0012 train_loss= 1.37633 train_acc= 0.31285 val_loss= 1.38208 val_acc= 0.23333 time= 0.01563
Epoch: 0013 train_loss= 1.37387 train_acc= 0.31425 val_loss= 1.38202 val_acc= 0.23333 time= 0.00000
Epoch: 0014 train_loss= 1.37488 train_acc= 0.31425 val_loss= 1.38199 val_acc= 0.23333 time= 0.01563
Epoch: 0015 train_loss= 1.37298 train_acc= 0.31285 val_loss= 1.38202 val_acc= 0.23333 time= 0.00000
Epoch: 0016 train_loss= 1.37276 train_acc= 0.31425 val_loss= 1.38211 val_acc= 0.23333 time= 0.01563
Epoch: 0017 train_loss= 1.37271 train_acc= 0.31425 val_loss= 1.38227 val_acc= 0.23333 time= 0.00000
Epoch: 0018 train_loss= 1.37190 train_acc= 0.31425 val_loss= 1.38244 val_acc= 0.23333 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 1.38315 accuracy= 0.31667 time= 0.00000 
