Epoch: 0001 train_loss= 0.70045 train_acc= 0.48909 val_loss= 0.69835 val_acc= 0.57377 time= 0.20963
Epoch: 0002 train_loss= 0.69920 train_acc= 0.49636 val_loss= 0.69913 val_acc= 0.42623 time= 0.01563
Epoch: 0003 train_loss= 0.69846 train_acc= 0.52364 val_loss= 0.69983 val_acc= 0.42623 time= 0.01563
Epoch: 0004 train_loss= 0.69771 train_acc= 0.51455 val_loss= 0.70059 val_acc= 0.42623 time= 0.01563
Epoch: 0005 train_loss= 0.69678 train_acc= 0.51091 val_loss= 0.70134 val_acc= 0.42623 time= 0.01563
Epoch: 0006 train_loss= 0.69645 train_acc= 0.51091 val_loss= 0.70186 val_acc= 0.42623 time= 0.01563
Epoch: 0007 train_loss= 0.69587 train_acc= 0.51091 val_loss= 0.70242 val_acc= 0.42623 time= 0.00000
Epoch: 0008 train_loss= 0.69515 train_acc= 0.51091 val_loss= 0.70306 val_acc= 0.42623 time= 0.01563
Epoch: 0009 train_loss= 0.69494 train_acc= 0.51091 val_loss= 0.70374 val_acc= 0.42623 time= 0.01563
Epoch: 0010 train_loss= 0.69423 train_acc= 0.51091 val_loss= 0.70449 val_acc= 0.42623 time= 0.01563
Epoch: 0011 train_loss= 0.69409 train_acc= 0.51091 val_loss= 0.70526 val_acc= 0.42623 time= 0.01563
Epoch: 0012 train_loss= 0.69390 train_acc= 0.51091 val_loss= 0.70600 val_acc= 0.42623 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.70523 accuracy= 0.44262 time= 0.00000 
