Epoch: 0001 train_loss= 0.69510 train_acc= 0.51818 val_loss= 0.69013 val_acc= 0.59016 time= 0.24205
Epoch: 0002 train_loss= 0.69306 train_acc= 0.52121 val_loss= 0.69042 val_acc= 0.59016 time= 0.00500
Epoch: 0003 train_loss= 0.69334 train_acc= 0.52727 val_loss= 0.69063 val_acc= 0.59016 time= 0.00400
Epoch: 0004 train_loss= 0.69268 train_acc= 0.52121 val_loss= 0.69086 val_acc= 0.59016 time= 0.00600
Epoch: 0005 train_loss= 0.69345 train_acc= 0.52121 val_loss= 0.69102 val_acc= 0.59016 time= 0.00500
Epoch: 0006 train_loss= 0.69317 train_acc= 0.52727 val_loss= 0.69122 val_acc= 0.59016 time= 0.00500
Epoch: 0007 train_loss= 0.69458 train_acc= 0.52424 val_loss= 0.69140 val_acc= 0.59016 time= 0.00600
Epoch: 0008 train_loss= 0.69308 train_acc= 0.51515 val_loss= 0.69148 val_acc= 0.59016 time= 0.00500
Epoch: 0009 train_loss= 0.69490 train_acc= 0.51212 val_loss= 0.69162 val_acc= 0.59016 time= 0.00500
Epoch: 0010 train_loss= 0.69304 train_acc= 0.52424 val_loss= 0.69177 val_acc= 0.59016 time= 0.00500
Epoch: 0011 train_loss= 0.69336 train_acc= 0.52727 val_loss= 0.69191 val_acc= 0.59016 time= 0.00400
Epoch: 0012 train_loss= 0.69370 train_acc= 0.50606 val_loss= 0.69198 val_acc= 0.59016 time= 0.00500
Early stopping...
Optimization Finished!
Test set results: cost= 0.69554 accuracy= 0.44262 time= 0.00200 
