Epoch: 0001 train_loss= 0.70104 train_acc= 0.51299 val_loss= 0.69731 val_acc= 0.65574 time= 0.35983
Epoch: 0002 train_loss= 0.69809 train_acc= 0.52338 val_loss= 0.69457 val_acc= 0.65574 time= 0.01028
Epoch: 0003 train_loss= 0.69599 train_acc= 0.51818 val_loss= 0.69277 val_acc= 0.65574 time= 0.01001
Epoch: 0004 train_loss= 0.69451 train_acc= 0.51818 val_loss= 0.69191 val_acc= 0.67213 time= 0.01011
Epoch: 0005 train_loss= 0.69373 train_acc= 0.52208 val_loss= 0.69137 val_acc= 0.67213 time= 0.00982
Epoch: 0006 train_loss= 0.69313 train_acc= 0.54156 val_loss= 0.69110 val_acc= 0.67213 time= 0.00972
Epoch: 0007 train_loss= 0.69292 train_acc= 0.54545 val_loss= 0.69074 val_acc= 0.67213 time= 0.00999
Epoch: 0008 train_loss= 0.69300 train_acc= 0.53766 val_loss= 0.69061 val_acc= 0.67213 time= 0.01046
Epoch: 0009 train_loss= 0.69274 train_acc= 0.55455 val_loss= 0.69062 val_acc= 0.68852 time= 0.00984
Epoch: 0010 train_loss= 0.69282 train_acc= 0.57273 val_loss= 0.69055 val_acc= 0.68852 time= 0.01972
Epoch: 0011 train_loss= 0.69298 train_acc= 0.54675 val_loss= 0.69088 val_acc= 0.70492 time= 0.01011
Epoch: 0012 train_loss= 0.69265 train_acc= 0.58831 val_loss= 0.69127 val_acc= 0.78689 time= 0.00990
Epoch: 0013 train_loss= 0.69280 train_acc= 0.57013 val_loss= 0.69155 val_acc= 0.81967 time= 0.01057
Early stopping...
Optimization Finished!
Test set results: cost= 0.69361 accuracy= 0.63115 time= 0.00000 
