Epoch: 0001 train_loss= 0.69686 train_acc= 0.54545 val_loss= 0.69015 val_acc= 0.63934 time= 0.18004
Epoch: 0002 train_loss= 0.69764 train_acc= 0.52727 val_loss= 0.68553 val_acc= 0.63934 time= 0.00500
Epoch: 0003 train_loss= 0.69739 train_acc= 0.53030 val_loss= 0.68205 val_acc= 0.63934 time= 0.00600
Epoch: 0004 train_loss= 0.69685 train_acc= 0.53333 val_loss= 0.67973 val_acc= 0.63934 time= 0.00400
Epoch: 0005 train_loss= 0.69539 train_acc= 0.54242 val_loss= 0.67839 val_acc= 0.63934 time= 0.00600
Epoch: 0006 train_loss= 0.69491 train_acc= 0.53636 val_loss= 0.67764 val_acc= 0.63934 time= 0.00500
Epoch: 0007 train_loss= 0.69430 train_acc= 0.54848 val_loss= 0.67774 val_acc= 0.63934 time= 0.00600
Epoch: 0008 train_loss= 0.69480 train_acc= 0.53636 val_loss= 0.67806 val_acc= 0.63934 time= 0.00500
Epoch: 0009 train_loss= 0.69498 train_acc= 0.54242 val_loss= 0.67901 val_acc= 0.63934 time= 0.00600
Epoch: 0010 train_loss= 0.69423 train_acc= 0.53939 val_loss= 0.68014 val_acc= 0.63934 time= 0.00500
Epoch: 0011 train_loss= 0.69419 train_acc= 0.52424 val_loss= 0.68119 val_acc= 0.63934 time= 0.00500
Epoch: 0012 train_loss= 0.69325 train_acc= 0.53636 val_loss= 0.68198 val_acc= 0.63934 time= 0.00500
Early stopping...
Optimization Finished!
Test set results: cost= 0.69366 accuracy= 0.53279 time= 0.00200 
