Epoch: 0001 train_loss= 1.42293 train_acc= 0.19870 val_loss= 1.38320 val_acc= 0.26786 time= 0.15626
Epoch: 0002 train_loss= 1.42091 train_acc= 0.21824 val_loss= 1.38758 val_acc= 0.21429 time= 0.01563
Epoch: 0003 train_loss= 1.40252 train_acc= 0.23779 val_loss= 1.39390 val_acc= 0.17857 time= 0.00000
Epoch: 0004 train_loss= 1.39327 train_acc= 0.22476 val_loss= 1.40185 val_acc= 0.25000 time= 0.01563
Epoch: 0005 train_loss= 1.39866 train_acc= 0.23779 val_loss= 1.41186 val_acc= 0.26786 time= 0.01563
Epoch: 0006 train_loss= 1.38305 train_acc= 0.28990 val_loss= 1.42326 val_acc= 0.28571 time= 0.01563
Epoch: 0007 train_loss= 1.37755 train_acc= 0.36156 val_loss= 1.43594 val_acc= 0.28571 time= 0.01563
Epoch: 0008 train_loss= 1.37682 train_acc= 0.32573 val_loss= 1.44562 val_acc= 0.28571 time= 0.01563
Epoch: 0009 train_loss= 1.38399 train_acc= 0.35179 val_loss= 1.45038 val_acc= 0.28571 time= 0.01563
Epoch: 0010 train_loss= 1.37263 train_acc= 0.34202 val_loss= 1.45338 val_acc= 0.28571 time= 0.01563
Epoch: 0011 train_loss= 1.36008 train_acc= 0.34528 val_loss= 1.45565 val_acc= 0.28571 time= 0.00000
Epoch: 0012 train_loss= 1.36287 train_acc= 0.34202 val_loss= 1.45726 val_acc= 0.28571 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38278 accuracy= 0.30973 time= 0.01563 
