Epoch: 0001 train_loss= 0.82687 train_acc= 0.46364 val_loss= 0.68152 val_acc= 0.52459 time= 0.09332
Epoch: 0002 train_loss= 0.82416 train_acc= 0.53333 val_loss= 0.68515 val_acc= 0.49180 time= 0.01563
Epoch: 0003 train_loss= 1.04141 train_acc= 0.57273 val_loss= 0.71572 val_acc= 0.45902 time= 0.00000
Epoch: 0004 train_loss= 0.71502 train_acc= 0.55455 val_loss= 0.78085 val_acc= 0.47541 time= 0.01563
Epoch: 0005 train_loss= 0.80002 train_acc= 0.46061 val_loss= 0.78102 val_acc= 0.45902 time= 0.01563
Epoch: 0006 train_loss= 0.80159 train_acc= 0.49394 val_loss= 0.75598 val_acc= 0.45902 time= 0.01562
Epoch: 0007 train_loss= 0.72297 train_acc= 0.55152 val_loss= 0.74294 val_acc= 0.44262 time= 0.01563
Epoch: 0008 train_loss= 1.02656 train_acc= 0.53333 val_loss= 0.74887 val_acc= 0.44262 time= 0.00000
Epoch: 0009 train_loss= 1.00492 train_acc= 0.45152 val_loss= 0.73365 val_acc= 0.47541 time= 0.01563
Epoch: 0010 train_loss= 0.93867 train_acc= 0.55152 val_loss= 0.73617 val_acc= 0.47541 time= 0.01563
Epoch: 0011 train_loss= 0.72001 train_acc= 0.53636 val_loss= 0.74071 val_acc= 0.45902 time= 0.01563
Epoch: 0012 train_loss= 0.78021 train_acc= 0.48182 val_loss= 0.73609 val_acc= 0.49180 time= 0.00000
Epoch: 0013 train_loss= 0.78638 train_acc= 0.50909 val_loss= 0.72765 val_acc= 0.42623 time= 0.01563
Epoch: 0014 train_loss= 0.82088 train_acc= 0.46667 val_loss= 0.71933 val_acc= 0.47541 time= 0.01563
Epoch: 0015 train_loss= 0.75531 train_acc= 0.55758 val_loss= 0.71714 val_acc= 0.50820 time= 0.01563
Epoch: 0016 train_loss= 0.71221 train_acc= 0.53333 val_loss= 0.71703 val_acc= 0.50820 time= 0.01563
Epoch: 0017 train_loss= 0.74760 train_acc= 0.50303 val_loss= 0.71764 val_acc= 0.49180 time= 0.00000
Epoch: 0018 train_loss= 0.70658 train_acc= 0.56364 val_loss= 0.71788 val_acc= 0.49180 time= 0.01563
Epoch: 0019 train_loss= 0.70473 train_acc= 0.48788 val_loss= 0.71811 val_acc= 0.50820 time= 0.01563
Epoch: 0020 train_loss= 0.70268 train_acc= 0.56667 val_loss= 0.71868 val_acc= 0.49180 time= 0.01563
Epoch: 0021 train_loss= 0.68743 train_acc= 0.56061 val_loss= 0.71927 val_acc= 0.49180 time= 0.01563
Epoch: 0022 train_loss= 0.71514 train_acc= 0.56970 val_loss= 0.71923 val_acc= 0.49180 time= 0.00000
Epoch: 0023 train_loss= 0.76631 train_acc= 0.51212 val_loss= 0.72040 val_acc= 0.49180 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.70951 accuracy= 0.46721 time= 0.00000 
