Epoch: 0001 train_loss= 2.08645 train_acc= 0.11321 val_loss= 2.08876 val_acc= 0.06897 time= 0.33054
Epoch: 0002 train_loss= 2.08443 train_acc= 0.11321 val_loss= 2.08715 val_acc= 0.06897 time= 0.01563
Epoch: 0003 train_loss= 2.08271 train_acc= 0.11321 val_loss= 2.08686 val_acc= 0.06897 time= 0.00000
Epoch: 0004 train_loss= 2.08142 train_acc= 0.11321 val_loss= 2.08723 val_acc= 0.06897 time= 0.01563
Epoch: 0005 train_loss= 2.08055 train_acc= 0.11321 val_loss= 2.08744 val_acc= 0.06897 time= 0.00000
Epoch: 0006 train_loss= 2.07955 train_acc= 0.11321 val_loss= 2.08758 val_acc= 0.06897 time= 0.01562
Epoch: 0007 train_loss= 2.07905 train_acc= 0.11321 val_loss= 2.08776 val_acc= 0.06897 time= 0.01563
Epoch: 0008 train_loss= 2.07771 train_acc= 0.11321 val_loss= 2.08787 val_acc= 0.06897 time= 0.00000
Epoch: 0009 train_loss= 2.07786 train_acc= 0.11321 val_loss= 2.08797 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.07644 train_acc= 0.11321 val_loss= 2.08813 val_acc= 0.06897 time= 0.00000
Epoch: 0011 train_loss= 2.07476 train_acc= 0.11321 val_loss= 2.08836 val_acc= 0.06897 time= 0.01563
Epoch: 0012 train_loss= 2.07421 train_acc= 0.11051 val_loss= 2.08858 val_acc= 0.06897 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.07948 accuracy= 0.08475 time= 0.00000 
