Epoch: 0001 train_loss= 0.70442 train_acc= 0.49740 val_loss= 0.72215 val_acc= 0.40984 time= 0.84380
Epoch: 0002 train_loss= 0.70023 train_acc= 0.48961 val_loss= 0.71732 val_acc= 0.40984 time= 0.01563
Epoch: 0003 train_loss= 0.69900 train_acc= 0.49091 val_loss= 0.71281 val_acc= 0.40984 time= 0.00000
Epoch: 0004 train_loss= 0.69900 train_acc= 0.48701 val_loss= 0.70864 val_acc= 0.40984 time= 0.00000
Epoch: 0005 train_loss= 0.69532 train_acc= 0.50260 val_loss= 0.70480 val_acc= 0.40984 time= 0.01563
Epoch: 0006 train_loss= 0.69692 train_acc= 0.50130 val_loss= 0.70131 val_acc= 0.40984 time= 0.00000
Epoch: 0007 train_loss= 0.69802 train_acc= 0.50649 val_loss= 0.69877 val_acc= 0.40984 time= 0.01563
Epoch: 0008 train_loss= 0.69429 train_acc= 0.51299 val_loss= 0.69661 val_acc= 0.42623 time= 0.00000
Epoch: 0009 train_loss= 0.69520 train_acc= 0.50000 val_loss= 0.69508 val_acc= 0.42623 time= 0.00000
Epoch: 0010 train_loss= 0.69586 train_acc= 0.46883 val_loss= 0.69389 val_acc= 0.42623 time= 0.01888
Epoch: 0011 train_loss= 0.69534 train_acc= 0.48052 val_loss= 0.69324 val_acc= 0.44262 time= 0.00203
Epoch: 0012 train_loss= 0.69576 train_acc= 0.48831 val_loss= 0.69297 val_acc= 0.52459 time= 0.01050
Epoch: 0013 train_loss= 0.69550 train_acc= 0.48052 val_loss= 0.69299 val_acc= 0.52459 time= 0.00000
Epoch: 0014 train_loss= 0.69703 train_acc= 0.45325 val_loss= 0.69332 val_acc= 0.42623 time= 0.00000
Epoch: 0015 train_loss= 0.69477 train_acc= 0.48831 val_loss= 0.69388 val_acc= 0.42623 time= 0.01563
Epoch: 0016 train_loss= 0.69536 train_acc= 0.48831 val_loss= 0.69461 val_acc= 0.39344 time= 0.00000
Epoch: 0017 train_loss= 0.69625 train_acc= 0.48052 val_loss= 0.69539 val_acc= 0.42623 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69371 accuracy= 0.48361 time= 0.01563 
