Epoch: 0001 train_loss= 2.08716 train_acc= 0.12938 val_loss= 2.08695 val_acc= 0.00000 time= 0.43753
Epoch: 0002 train_loss= 2.08475 train_acc= 0.12938 val_loss= 2.08647 val_acc= 0.00000 time= 0.00000
Epoch: 0003 train_loss= 2.08289 train_acc= 0.13208 val_loss= 2.08613 val_acc= 0.00000 time= 0.01563
Epoch: 0004 train_loss= 2.08104 train_acc= 0.13747 val_loss= 2.08598 val_acc= 0.13793 time= 0.00000
Epoch: 0005 train_loss= 2.07965 train_acc= 0.17251 val_loss= 2.08602 val_acc= 0.13793 time= 0.01563
Epoch: 0006 train_loss= 2.07808 train_acc= 0.15364 val_loss= 2.08626 val_acc= 0.13793 time= 0.01563
Epoch: 0007 train_loss= 2.07747 train_acc= 0.15633 val_loss= 2.08649 val_acc= 0.13793 time= 0.00000
Epoch: 0008 train_loss= 2.07636 train_acc= 0.15633 val_loss= 2.08668 val_acc= 0.13793 time= 0.01563
Epoch: 0009 train_loss= 2.07527 train_acc= 0.15633 val_loss= 2.08675 val_acc= 0.13793 time= 0.01563
Epoch: 0010 train_loss= 2.07398 train_acc= 0.15633 val_loss= 2.08675 val_acc= 0.13793 time= 0.00000
Epoch: 0011 train_loss= 2.07345 train_acc= 0.15633 val_loss= 2.08676 val_acc= 0.13793 time= 0.01563
Epoch: 0012 train_loss= 2.07377 train_acc= 0.15633 val_loss= 2.08662 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.06350 accuracy= 0.13559 time= 0.01563 
