Epoch: 0001 train_loss= 0.69692 train_acc= 0.47273 val_loss= 0.69654 val_acc= 0.39344 time= 0.55097
Epoch: 0002 train_loss= 0.69738 train_acc= 0.46545 val_loss= 0.69203 val_acc= 0.60656 time= 0.01521
Epoch: 0003 train_loss= 0.69620 train_acc= 0.52182 val_loss= 0.68836 val_acc= 0.60656 time= 0.00000
Epoch: 0004 train_loss= 0.69321 train_acc= 0.52000 val_loss= 0.68559 val_acc= 0.60656 time= 0.01562
Epoch: 0005 train_loss= 0.69421 train_acc= 0.51818 val_loss= 0.68360 val_acc= 0.60656 time= 0.00000
Epoch: 0006 train_loss= 0.69500 train_acc= 0.51455 val_loss= 0.68229 val_acc= 0.60656 time= 0.00000
Epoch: 0007 train_loss= 0.69385 train_acc= 0.51455 val_loss= 0.68162 val_acc= 0.60656 time= 0.01563
Epoch: 0008 train_loss= 0.69245 train_acc= 0.52727 val_loss= 0.68138 val_acc= 0.60656 time= 0.00000
Epoch: 0009 train_loss= 0.69452 train_acc= 0.52000 val_loss= 0.68149 val_acc= 0.60656 time= 0.00000
Epoch: 0010 train_loss= 0.69257 train_acc= 0.53091 val_loss= 0.68180 val_acc= 0.60656 time= 0.01563
Epoch: 0011 train_loss= 0.69251 train_acc= 0.51818 val_loss= 0.68241 val_acc= 0.60656 time= 0.00000
Epoch: 0012 train_loss= 0.69531 train_acc= 0.52182 val_loss= 0.68317 val_acc= 0.60656 time= 0.00000
Epoch: 0013 train_loss= 0.69282 train_acc= 0.52364 val_loss= 0.68393 val_acc= 0.60656 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69218 accuracy= 0.52459 time= 0.01563 
