Epoch: 0001 train_loss= 1.39343 train_acc= 0.24430 val_loss= 1.37831 val_acc= 0.39286 time= 0.12501
Epoch: 0002 train_loss= 1.39613 train_acc= 0.21173 val_loss= 1.37183 val_acc= 0.39286 time= 0.01563
Epoch: 0003 train_loss= 1.39104 train_acc= 0.26710 val_loss= 1.36631 val_acc= 0.39286 time= 0.01563
Epoch: 0004 train_loss= 1.38263 train_acc= 0.29967 val_loss= 1.36211 val_acc= 0.39286 time= 0.00000
Epoch: 0005 train_loss= 1.40016 train_acc= 0.29642 val_loss= 1.36006 val_acc= 0.39286 time= 0.01563
Epoch: 0006 train_loss= 1.37771 train_acc= 0.29967 val_loss= 1.35841 val_acc= 0.39286 time= 0.01563
Epoch: 0007 train_loss= 1.38143 train_acc= 0.30619 val_loss= 1.35681 val_acc= 0.39286 time= 0.01563
Epoch: 0008 train_loss= 1.38487 train_acc= 0.30293 val_loss= 1.35511 val_acc= 0.39286 time= 0.01563
Epoch: 0009 train_loss= 1.38760 train_acc= 0.30619 val_loss= 1.35426 val_acc= 0.39286 time= 0.01563
Epoch: 0010 train_loss= 1.37557 train_acc= 0.30619 val_loss= 1.35388 val_acc= 0.39286 time= 0.00000
Epoch: 0011 train_loss= 1.38838 train_acc= 0.30293 val_loss= 1.35338 val_acc= 0.39286 time= 0.01563
Epoch: 0012 train_loss= 1.36885 train_acc= 0.31596 val_loss= 1.35268 val_acc= 0.39286 time= 0.01562
Epoch: 0013 train_loss= 1.37446 train_acc= 0.30293 val_loss= 1.35180 val_acc= 0.39286 time= 0.01563
Epoch: 0014 train_loss= 1.37716 train_acc= 0.31596 val_loss= 1.35116 val_acc= 0.39286 time= 0.01563
Epoch: 0015 train_loss= 1.37652 train_acc= 0.31922 val_loss= 1.35099 val_acc= 0.41071 time= 0.00000
Epoch: 0016 train_loss= 1.37400 train_acc= 0.30619 val_loss= 1.35116 val_acc= 0.41071 time= 0.01563
Epoch: 0017 train_loss= 1.37629 train_acc= 0.31270 val_loss= 1.35154 val_acc= 0.41071 time= 0.01563
Epoch: 0018 train_loss= 1.37229 train_acc= 0.33225 val_loss= 1.35175 val_acc= 0.39286 time= 0.00000
Epoch: 0019 train_loss= 1.37643 train_acc= 0.29967 val_loss= 1.35156 val_acc= 0.35714 time= 0.01563
Epoch: 0020 train_loss= 1.37106 train_acc= 0.32899 val_loss= 1.35123 val_acc= 0.33929 time= 0.01563
Epoch: 0021 train_loss= 1.36527 train_acc= 0.31922 val_loss= 1.35085 val_acc= 0.32143 time= 0.01563
Epoch: 0022 train_loss= 1.37118 train_acc= 0.31922 val_loss= 1.35078 val_acc= 0.33929 time= 0.01563
Epoch: 0023 train_loss= 1.36831 train_acc= 0.31596 val_loss= 1.35018 val_acc= 0.35714 time= 0.01563
Epoch: 0024 train_loss= 1.37026 train_acc= 0.32248 val_loss= 1.34910 val_acc= 0.37500 time= 0.00000
Epoch: 0025 train_loss= 1.37008 train_acc= 0.33876 val_loss= 1.34788 val_acc= 0.37500 time= 0.01563
Epoch: 0026 train_loss= 1.36865 train_acc= 0.33225 val_loss= 1.34705 val_acc= 0.37500 time= 0.01563
Epoch: 0027 train_loss= 1.36454 train_acc= 0.31922 val_loss= 1.34590 val_acc= 0.39286 time= 0.01563
Epoch: 0028 train_loss= 1.36682 train_acc= 0.32248 val_loss= 1.34448 val_acc= 0.37500 time= 0.00000
Epoch: 0029 train_loss= 1.37354 train_acc= 0.35831 val_loss= 1.34323 val_acc= 0.39286 time= 0.01563
Epoch: 0030 train_loss= 1.36413 train_acc= 0.33550 val_loss= 1.34200 val_acc= 0.37500 time= 0.01562
Epoch: 0031 train_loss= 1.36525 train_acc= 0.33550 val_loss= 1.34110 val_acc= 0.37500 time= 0.01563
Epoch: 0032 train_loss= 1.36752 train_acc= 0.31270 val_loss= 1.34058 val_acc= 0.37500 time= 0.00000
Epoch: 0033 train_loss= 1.36708 train_acc= 0.30619 val_loss= 1.34031 val_acc= 0.37500 time= 0.01563
Epoch: 0034 train_loss= 1.35564 train_acc= 0.32248 val_loss= 1.34025 val_acc= 0.39286 time= 0.01563
Epoch: 0035 train_loss= 1.37007 train_acc= 0.33876 val_loss= 1.34034 val_acc= 0.41071 time= 0.01562
Epoch: 0036 train_loss= 1.36137 train_acc= 0.32899 val_loss= 1.34045 val_acc= 0.41071 time= 0.00000
Epoch: 0037 train_loss= 1.36305 train_acc= 0.32248 val_loss= 1.34027 val_acc= 0.41071 time= 0.01563
Epoch: 0038 train_loss= 1.36128 train_acc= 0.32573 val_loss= 1.34046 val_acc= 0.42857 time= 0.01563
Epoch: 0039 train_loss= 1.36296 train_acc= 0.34853 val_loss= 1.34090 val_acc= 0.42857 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 1.38180 accuracy= 0.30973 time= 0.00000 
