Epoch: 0001 train_loss= 1.42432 train_acc= 0.21173 val_loss= 1.45341 val_acc= 0.23214 time= 0.14088
Epoch: 0002 train_loss= 1.40127 train_acc= 0.28339 val_loss= 1.45204 val_acc= 0.28571 time= 0.01538
Epoch: 0003 train_loss= 1.40125 train_acc= 0.31596 val_loss= 1.44912 val_acc= 0.33929 time= 0.01563
Epoch: 0004 train_loss= 1.38409 train_acc= 0.30619 val_loss= 1.44839 val_acc= 0.32143 time= 0.01563
Epoch: 0005 train_loss= 1.41539 train_acc= 0.29316 val_loss= 1.44229 val_acc= 0.35714 time= 0.01563
Epoch: 0006 train_loss= 1.39327 train_acc= 0.29642 val_loss= 1.43537 val_acc= 0.39286 time= 0.00000
Epoch: 0007 train_loss= 1.38644 train_acc= 0.29642 val_loss= 1.42875 val_acc= 0.39286 time= 0.01563
Epoch: 0008 train_loss= 1.38765 train_acc= 0.30293 val_loss= 1.42283 val_acc= 0.37500 time= 0.01563
Epoch: 0009 train_loss= 1.38412 train_acc= 0.31922 val_loss= 1.41629 val_acc= 0.35714 time= 0.01563
Epoch: 0010 train_loss= 1.38531 train_acc= 0.29642 val_loss= 1.41151 val_acc= 0.33929 time= 0.01563
Epoch: 0011 train_loss= 1.38874 train_acc= 0.32573 val_loss= 1.40644 val_acc= 0.28571 time= 0.00492
Epoch: 0012 train_loss= 1.37900 train_acc= 0.32573 val_loss= 1.40195 val_acc= 0.26786 time= 0.01101
Epoch: 0013 train_loss= 1.38672 train_acc= 0.31922 val_loss= 1.39676 val_acc= 0.28571 time= 0.01563
Epoch: 0014 train_loss= 1.37933 train_acc= 0.33550 val_loss= 1.39189 val_acc= 0.28571 time= 0.01563
Epoch: 0015 train_loss= 1.37723 train_acc= 0.29642 val_loss= 1.38766 val_acc= 0.30357 time= 0.01563
Epoch: 0016 train_loss= 1.37276 train_acc= 0.32248 val_loss= 1.38433 val_acc= 0.30357 time= 0.00000
Epoch: 0017 train_loss= 1.37767 train_acc= 0.28339 val_loss= 1.38108 val_acc= 0.30357 time= 0.01563
Epoch: 0018 train_loss= 1.38102 train_acc= 0.31270 val_loss= 1.37872 val_acc= 0.30357 time= 0.01563
Epoch: 0019 train_loss= 1.37553 train_acc= 0.34202 val_loss= 1.37711 val_acc= 0.33929 time= 0.01562
Epoch: 0020 train_loss= 1.37869 train_acc= 0.32573 val_loss= 1.37603 val_acc= 0.37500 time= 0.00000
Epoch: 0021 train_loss= 1.37822 train_acc= 0.31270 val_loss= 1.37509 val_acc= 0.39286 time= 0.01563
Epoch: 0022 train_loss= 1.36717 train_acc= 0.31596 val_loss= 1.37485 val_acc= 0.37500 time= 0.01562
Epoch: 0023 train_loss= 1.36620 train_acc= 0.33550 val_loss= 1.37479 val_acc= 0.37500 time= 0.01563
Epoch: 0024 train_loss= 1.37031 train_acc= 0.32248 val_loss= 1.37505 val_acc= 0.37500 time= 0.01563
Epoch: 0025 train_loss= 1.38544 train_acc= 0.30293 val_loss= 1.37594 val_acc= 0.37500 time= 0.01562
Epoch: 0026 train_loss= 1.36188 train_acc= 0.34202 val_loss= 1.37684 val_acc= 0.37500 time= 0.01563
Epoch: 0027 train_loss= 1.36904 train_acc= 0.34202 val_loss= 1.37797 val_acc= 0.35714 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.37583 accuracy= 0.32743 time= 0.01562 
