Epoch: 0001 train_loss= 2.08711 train_acc= 0.16981 val_loss= 2.08633 val_acc= 0.06897 time= 0.45356
Epoch: 0002 train_loss= 2.08477 train_acc= 0.16226 val_loss= 2.08627 val_acc= 0.06897 time= 0.00000
Epoch: 0003 train_loss= 2.08240 train_acc= 0.16604 val_loss= 2.08665 val_acc= 0.06897 time= 0.01563
Epoch: 0004 train_loss= 2.07989 train_acc= 0.16981 val_loss= 2.08750 val_acc= 0.06897 time= 0.01563
Epoch: 0005 train_loss= 2.07786 train_acc= 0.16604 val_loss= 2.08891 val_acc= 0.06897 time= 0.00000
Epoch: 0006 train_loss= 2.07578 train_acc= 0.16226 val_loss= 2.09097 val_acc= 0.06897 time= 0.01563
Epoch: 0007 train_loss= 2.07427 train_acc= 0.16604 val_loss= 2.09356 val_acc= 0.06897 time= 0.03125
Epoch: 0008 train_loss= 2.07158 train_acc= 0.16604 val_loss= 2.09681 val_acc= 0.06897 time= 0.00000
Epoch: 0009 train_loss= 2.07065 train_acc= 0.16981 val_loss= 2.10040 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.06883 train_acc= 0.16981 val_loss= 2.10444 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.06602 train_acc= 0.17736 val_loss= 2.10891 val_acc= 0.06897 time= 0.00000
Epoch: 0012 train_loss= 2.06440 train_acc= 0.17358 val_loss= 2.11383 val_acc= 0.06897 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.07321 accuracy= 0.11864 time= 0.00000 
