Epoch: 0001 train_loss= 1.44664 train_acc= 0.23633 val_loss= 1.38963 val_acc= 0.30357 time= 0.51652
Epoch: 0002 train_loss= 1.40088 train_acc= 0.27734 val_loss= 1.38753 val_acc= 0.33929 time= 0.02018
Epoch: 0003 train_loss= 1.40790 train_acc= 0.29297 val_loss= 1.38708 val_acc= 0.32143 time= 0.02024
Epoch: 0004 train_loss= 1.39224 train_acc= 0.29688 val_loss= 1.38835 val_acc= 0.32143 time= 0.01833
Epoch: 0005 train_loss= 1.38264 train_acc= 0.30664 val_loss= 1.39063 val_acc= 0.33929 time= 0.01718
Epoch: 0006 train_loss= 1.38506 train_acc= 0.29492 val_loss= 1.39319 val_acc= 0.37500 time= 0.01608
Epoch: 0007 train_loss= 1.38171 train_acc= 0.28516 val_loss= 1.39636 val_acc= 0.37500 time= 0.01657
Epoch: 0008 train_loss= 1.38439 train_acc= 0.30859 val_loss= 1.39956 val_acc= 0.35714 time= 0.01500
Epoch: 0009 train_loss= 1.38201 train_acc= 0.31445 val_loss= 1.40177 val_acc= 0.30357 time= 0.01600
Epoch: 0010 train_loss= 1.38081 train_acc= 0.31250 val_loss= 1.40331 val_acc= 0.28571 time= 0.01514
Epoch: 0011 train_loss= 1.38388 train_acc= 0.30664 val_loss= 1.40383 val_acc= 0.26786 time= 0.01420
Epoch: 0012 train_loss= 1.37869 train_acc= 0.32422 val_loss= 1.40395 val_acc= 0.26786 time= 0.01524
Early stopping...
Optimization Finished!
Test set results: cost= 1.38955 accuracy= 0.30088 time= 0.00588 
