Epoch: 0001 train_loss= 0.70108 train_acc= 0.46234 val_loss= 0.69830 val_acc= 0.44262 time= 0.37502
Epoch: 0002 train_loss= 0.69817 train_acc= 0.52338 val_loss= 0.69684 val_acc= 0.44262 time= 0.00000
Epoch: 0003 train_loss= 0.69596 train_acc= 0.52987 val_loss= 0.69637 val_acc= 0.42623 time= 0.01563
Epoch: 0004 train_loss= 0.69426 train_acc= 0.52987 val_loss= 0.69678 val_acc= 0.42623 time= 0.01563
Epoch: 0005 train_loss= 0.69309 train_acc= 0.53117 val_loss= 0.69782 val_acc= 0.42623 time= 0.01563
Epoch: 0006 train_loss= 0.69240 train_acc= 0.52987 val_loss= 0.69920 val_acc= 0.42623 time= 0.00000
Epoch: 0007 train_loss= 0.69198 train_acc= 0.52987 val_loss= 0.70084 val_acc= 0.42623 time= 0.01563
Epoch: 0008 train_loss= 0.69192 train_acc= 0.52987 val_loss= 0.70259 val_acc= 0.42623 time= 0.01563
Epoch: 0009 train_loss= 0.69218 train_acc= 0.53117 val_loss= 0.70425 val_acc= 0.42623 time= 0.01563
Epoch: 0010 train_loss= 0.69204 train_acc= 0.52987 val_loss= 0.70563 val_acc= 0.42623 time= 0.00000
Epoch: 0011 train_loss= 0.69184 train_acc= 0.52987 val_loss= 0.70642 val_acc= 0.42623 time= 0.01563
Epoch: 0012 train_loss= 0.69185 train_acc= 0.53117 val_loss= 0.70693 val_acc= 0.42623 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69976 accuracy= 0.46721 time= 0.00000 
