Epoch: 0001 train_loss= 1.65691 train_acc= 0.25586 val_loss= 1.44389 val_acc= 0.33929 time= 0.59379
Epoch: 0002 train_loss= 1.75888 train_acc= 0.31641 val_loss= 1.59052 val_acc= 0.33929 time= 0.01563
Epoch: 0003 train_loss= 1.77744 train_acc= 0.29688 val_loss= 1.53900 val_acc= 0.33929 time= 0.03125
Epoch: 0004 train_loss= 1.76267 train_acc= 0.26953 val_loss= 1.39854 val_acc= 0.30357 time= 0.01563
Epoch: 0005 train_loss= 1.49713 train_acc= 0.30469 val_loss= 1.35453 val_acc= 0.35714 time= 0.01563
Epoch: 0006 train_loss= 1.53554 train_acc= 0.26172 val_loss= 1.35129 val_acc= 0.37500 time= 0.03125
Epoch: 0007 train_loss= 1.63397 train_acc= 0.31250 val_loss= 1.35179 val_acc= 0.37500 time= 0.01563
Epoch: 0008 train_loss= 1.50547 train_acc= 0.29492 val_loss= 1.35073 val_acc= 0.37500 time= 0.03125
Epoch: 0009 train_loss= 1.74230 train_acc= 0.32617 val_loss= 1.35473 val_acc= 0.33929 time= 0.01562
Epoch: 0010 train_loss= 1.39649 train_acc= 0.29492 val_loss= 1.37897 val_acc= 0.30357 time= 0.01563
Epoch: 0011 train_loss= 1.42778 train_acc= 0.29297 val_loss= 1.38085 val_acc= 0.30357 time= 0.03125
Epoch: 0012 train_loss= 1.47832 train_acc= 0.25977 val_loss= 1.38074 val_acc= 0.30357 time= 0.01563
Epoch: 0013 train_loss= 1.37999 train_acc= 0.31836 val_loss= 1.38023 val_acc= 0.32143 time= 0.03125
Epoch: 0014 train_loss= 1.42203 train_acc= 0.26172 val_loss= 1.37915 val_acc= 0.32143 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.39023 accuracy= 0.28319 time= 0.01563 
