Epoch: 0001 train_loss= 1.39439 train_acc= 0.19218 val_loss= 1.39166 val_acc= 0.30357 time= 0.10938
Epoch: 0002 train_loss= 1.39275 train_acc= 0.24430 val_loss= 1.39054 val_acc= 0.30357 time= 0.01563
Epoch: 0003 train_loss= 1.39127 train_acc= 0.29316 val_loss= 1.38946 val_acc= 0.30357 time= 0.01563
Epoch: 0004 train_loss= 1.38969 train_acc= 0.29642 val_loss= 1.38848 val_acc= 0.30357 time= 0.01563
Epoch: 0005 train_loss= 1.38875 train_acc= 0.29316 val_loss= 1.38792 val_acc= 0.30357 time= 0.00000
Epoch: 0006 train_loss= 1.38729 train_acc= 0.30619 val_loss= 1.38737 val_acc= 0.30357 time= 0.01563
Epoch: 0007 train_loss= 1.38617 train_acc= 0.26710 val_loss= 1.38685 val_acc= 0.30357 time= 0.01563
Epoch: 0008 train_loss= 1.38579 train_acc= 0.27036 val_loss= 1.38640 val_acc= 0.30357 time= 0.01563
Epoch: 0009 train_loss= 1.38459 train_acc= 0.27036 val_loss= 1.38610 val_acc= 0.30357 time= 0.01563
Epoch: 0010 train_loss= 1.38462 train_acc= 0.27687 val_loss= 1.38595 val_acc= 0.30357 time= 0.01563
Epoch: 0011 train_loss= 1.38284 train_acc= 0.26384 val_loss= 1.38592 val_acc= 0.30357 time= 0.01563
Epoch: 0012 train_loss= 1.38276 train_acc= 0.29316 val_loss= 1.38604 val_acc= 0.30357 time= 0.01563
Epoch: 0013 train_loss= 1.38234 train_acc= 0.26384 val_loss= 1.38628 val_acc= 0.30357 time= 0.01563
Epoch: 0014 train_loss= 1.38212 train_acc= 0.28339 val_loss= 1.38651 val_acc= 0.30357 time= 0.01563
Epoch: 0015 train_loss= 1.38129 train_acc= 0.29967 val_loss= 1.38666 val_acc= 0.30357 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37463 accuracy= 0.30973 time= 0.00000 
