Epoch: 0001 train_loss= 2.12439 train_acc= 0.13208 val_loss= 2.07271 val_acc= 0.17241 time= 0.12501
Epoch: 0002 train_loss= 2.12337 train_acc= 0.13836 val_loss= 2.07286 val_acc= 0.17241 time= 0.01563
Epoch: 0003 train_loss= 2.10193 train_acc= 0.11321 val_loss= 2.07389 val_acc= 0.17241 time= 0.00000
Epoch: 0004 train_loss= 2.09097 train_acc= 0.13836 val_loss= 2.07446 val_acc= 0.17241 time= 0.01563
Epoch: 0005 train_loss= 2.09022 train_acc= 0.13208 val_loss= 2.07507 val_acc= 0.17241 time= 0.00000
Epoch: 0006 train_loss= 2.10053 train_acc= 0.08805 val_loss= 2.07574 val_acc= 0.17241 time= 0.01563
Epoch: 0007 train_loss= 2.08193 train_acc= 0.12579 val_loss= 2.07615 val_acc= 0.13793 time= 0.00000
Epoch: 0008 train_loss= 2.06695 train_acc= 0.14465 val_loss= 2.07651 val_acc= 0.10345 time= 0.00000
Epoch: 0009 train_loss= 2.07225 train_acc= 0.16981 val_loss= 2.07734 val_acc= 0.10345 time= 0.01563
Epoch: 0010 train_loss= 2.07632 train_acc= 0.15094 val_loss= 2.07837 val_acc= 0.10345 time= 0.00000
Epoch: 0011 train_loss= 2.05777 train_acc= 0.15723 val_loss= 2.07931 val_acc= 0.10345 time= 0.01563
Epoch: 0012 train_loss= 2.07482 train_acc= 0.15723 val_loss= 2.08031 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08495 accuracy= 0.16949 time= 0.01563 
