Epoch: 0001 train_loss= 2.08736 train_acc= 0.15723 val_loss= 2.08562 val_acc= 0.13793 time= 0.14064
Epoch: 0002 train_loss= 2.08492 train_acc= 0.15723 val_loss= 2.08438 val_acc= 0.13793 time= 0.01562
Epoch: 0003 train_loss= 2.08287 train_acc= 0.15723 val_loss= 2.08354 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.08094 train_acc= 0.15723 val_loss= 2.08307 val_acc= 0.13793 time= 0.02098
Epoch: 0005 train_loss= 2.07948 train_acc= 0.15723 val_loss= 2.08289 val_acc= 0.13793 time= 0.01106
Epoch: 0006 train_loss= 2.07760 train_acc= 0.15723 val_loss= 2.08301 val_acc= 0.13793 time= 0.00000
Epoch: 0007 train_loss= 2.07613 train_acc= 0.15723 val_loss= 2.08341 val_acc= 0.13793 time= 0.01563
Epoch: 0008 train_loss= 2.07550 train_acc= 0.15094 val_loss= 2.08401 val_acc= 0.13793 time= 0.01563
Epoch: 0009 train_loss= 2.07332 train_acc= 0.17610 val_loss= 2.08469 val_acc= 0.13793 time= 0.00000
Epoch: 0010 train_loss= 2.07232 train_acc= 0.15094 val_loss= 2.08543 val_acc= 0.13793 time= 0.01563
Epoch: 0011 train_loss= 2.07137 train_acc= 0.15094 val_loss= 2.08620 val_acc= 0.17241 time= 0.01563
Epoch: 0012 train_loss= 2.07073 train_acc= 0.18868 val_loss= 2.08691 val_acc= 0.20690 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.05855 accuracy= 0.20339 time= 0.01563 
