Epoch: 0001 train_loss= 1.39632 train_acc= 0.18945 val_loss= 1.38991 val_acc= 0.25000 time= 0.57842
Epoch: 0002 train_loss= 1.39182 train_acc= 0.19727 val_loss= 1.38862 val_acc= 0.25000 time= 0.00000
Epoch: 0003 train_loss= 1.38956 train_acc= 0.19727 val_loss= 1.38752 val_acc= 0.25000 time= 0.01562
Epoch: 0004 train_loss= 1.38851 train_acc= 0.25391 val_loss= 1.38659 val_acc= 0.28571 time= 0.00000
Epoch: 0005 train_loss= 1.38697 train_acc= 0.26172 val_loss= 1.38584 val_acc= 0.28571 time= 0.00000
Epoch: 0006 train_loss= 1.38495 train_acc= 0.29688 val_loss= 1.38525 val_acc= 0.28571 time= 0.01563
Epoch: 0007 train_loss= 1.38392 train_acc= 0.28125 val_loss= 1.38481 val_acc= 0.28571 time= 0.00000
Epoch: 0008 train_loss= 1.38250 train_acc= 0.29102 val_loss= 1.38452 val_acc= 0.28571 time= 0.01563
Epoch: 0009 train_loss= 1.38189 train_acc= 0.29688 val_loss= 1.38436 val_acc= 0.28571 time= 0.00000
Epoch: 0010 train_loss= 1.38185 train_acc= 0.29297 val_loss= 1.38434 val_acc= 0.28571 time= 0.00000
Epoch: 0011 train_loss= 1.37945 train_acc= 0.29102 val_loss= 1.38442 val_acc= 0.28571 time= 0.01563
Epoch: 0012 train_loss= 1.38078 train_acc= 0.29297 val_loss= 1.38461 val_acc= 0.28571 time= 0.00000
Epoch: 0013 train_loss= 1.37857 train_acc= 0.29297 val_loss= 1.38490 val_acc= 0.28571 time= 0.01563
Epoch: 0014 train_loss= 1.37975 train_acc= 0.28711 val_loss= 1.38527 val_acc= 0.28571 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.37412 accuracy= 0.30973 time= 0.00000 
