Epoch: 0001 train_loss= 2.08568 train_acc= 0.15094 val_loss= 2.08571 val_acc= 0.13793 time= 0.21876
Epoch: 0002 train_loss= 2.08392 train_acc= 0.14340 val_loss= 2.08442 val_acc= 0.13793 time= 0.00000
Epoch: 0003 train_loss= 2.08154 train_acc= 0.14717 val_loss= 2.08349 val_acc= 0.13793 time= 0.01563
Epoch: 0004 train_loss= 2.07987 train_acc= 0.15849 val_loss= 2.08298 val_acc= 0.13793 time= 0.01563
Epoch: 0005 train_loss= 2.07806 train_acc= 0.18868 val_loss= 2.08254 val_acc= 0.03448 time= 0.00000
Epoch: 0006 train_loss= 2.07660 train_acc= 0.21132 val_loss= 2.08217 val_acc= 0.03448 time= 0.01563
Epoch: 0007 train_loss= 2.07484 train_acc= 0.18868 val_loss= 2.08186 val_acc= 0.03448 time= 0.01562
Epoch: 0008 train_loss= 2.07383 train_acc= 0.20755 val_loss= 2.08166 val_acc= 0.03448 time= 0.00000
Epoch: 0009 train_loss= 2.07065 train_acc= 0.18868 val_loss= 2.08164 val_acc= 0.03448 time= 0.01563
Epoch: 0010 train_loss= 2.06946 train_acc= 0.20000 val_loss= 2.08176 val_acc= 0.03448 time= 0.01563
Epoch: 0011 train_loss= 2.06834 train_acc= 0.20377 val_loss= 2.08199 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.06604 train_acc= 0.21132 val_loss= 2.08233 val_acc= 0.03448 time= 0.01563
Epoch: 0013 train_loss= 2.06445 train_acc= 0.19623 val_loss= 2.08280 val_acc= 0.03448 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07713 accuracy= 0.18644 time= 0.00000 
