Epoch: 0001 train_loss= 1.44117 train_acc= 0.20810 val_loss= 1.38772 val_acc= 0.18333 time= 0.31252
Epoch: 0002 train_loss= 1.42378 train_acc= 0.19553 val_loss= 1.38031 val_acc= 0.26667 time= 0.03125
Epoch: 0003 train_loss= 1.41870 train_acc= 0.24162 val_loss= 1.37499 val_acc= 0.35000 time= 0.01563
Epoch: 0004 train_loss= 1.40987 train_acc= 0.26816 val_loss= 1.37148 val_acc= 0.38333 time= 0.01563
Epoch: 0005 train_loss= 1.39164 train_acc= 0.31564 val_loss= 1.36927 val_acc= 0.38333 time= 0.01563
Epoch: 0006 train_loss= 1.39180 train_acc= 0.31704 val_loss= 1.36777 val_acc= 0.38333 time= 0.01562
Epoch: 0007 train_loss= 1.39073 train_acc= 0.31145 val_loss= 1.36733 val_acc= 0.38333 time= 0.01563
Epoch: 0008 train_loss= 1.38605 train_acc= 0.32542 val_loss= 1.36731 val_acc= 0.38333 time= 0.03125
Epoch: 0009 train_loss= 1.39378 train_acc= 0.32402 val_loss= 1.36719 val_acc= 0.38333 time= 0.01563
Epoch: 0010 train_loss= 1.38253 train_acc= 0.32402 val_loss= 1.36740 val_acc= 0.38333 time= 0.01563
Epoch: 0011 train_loss= 1.38308 train_acc= 0.32542 val_loss= 1.36756 val_acc= 0.38333 time= 0.01563
Epoch: 0012 train_loss= 1.37857 train_acc= 0.31983 val_loss= 1.36816 val_acc= 0.38333 time= 0.01563
Epoch: 0013 train_loss= 1.37873 train_acc= 0.32402 val_loss= 1.36880 val_acc= 0.38333 time= 0.01563
Epoch: 0014 train_loss= 1.37662 train_acc= 0.32682 val_loss= 1.36936 val_acc= 0.38333 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 1.39882 accuracy= 0.31667 time= 0.00000 
