Epoch: 0001 train_loss= 2.11118 train_acc= 0.14717 val_loss= 2.08469 val_acc= 0.20690 time= 0.15627
Epoch: 0002 train_loss= 2.09433 train_acc= 0.14340 val_loss= 2.08895 val_acc= 0.13793 time= 0.01562
Epoch: 0003 train_loss= 2.09733 train_acc= 0.17358 val_loss= 2.09346 val_acc= 0.10345 time= 0.01563
Epoch: 0004 train_loss= 2.09441 train_acc= 0.15472 val_loss= 2.09839 val_acc= 0.06897 time= 0.00000
Epoch: 0005 train_loss= 2.09040 train_acc= 0.16981 val_loss= 2.10351 val_acc= 0.06897 time= 0.01563
Epoch: 0006 train_loss= 2.07233 train_acc= 0.16981 val_loss= 2.10887 val_acc= 0.06897 time= 0.01563
Epoch: 0007 train_loss= 2.06721 train_acc= 0.16604 val_loss= 2.11413 val_acc= 0.06897 time= 0.01562
Epoch: 0008 train_loss= 2.06977 train_acc= 0.16981 val_loss= 2.11997 val_acc= 0.06897 time= 0.00000
Epoch: 0009 train_loss= 2.05928 train_acc= 0.16981 val_loss= 2.12571 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.06721 train_acc= 0.16981 val_loss= 2.13184 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.06052 train_acc= 0.16981 val_loss= 2.13813 val_acc= 0.06897 time= 0.00000
Epoch: 0012 train_loss= 2.06094 train_acc= 0.16981 val_loss= 2.14369 val_acc= 0.06897 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.08354 accuracy= 0.10169 time= 0.00000 
