Epoch: 0001 train_loss= 2.06064 train_acc= 0.47091 val_loss= 0.81016 val_acc= 0.57377 time= 0.62504
Epoch: 0002 train_loss= 0.88216 train_acc= 0.50727 val_loss= 0.80945 val_acc= 0.44262 time= 0.01563
Epoch: 0003 train_loss= 0.77844 train_acc= 0.50727 val_loss= 0.95013 val_acc= 0.44262 time= 0.01563
Epoch: 0004 train_loss= 0.80186 train_acc= 0.51818 val_loss= 1.04659 val_acc= 0.44262 time= 0.03125
Epoch: 0005 train_loss= 0.91523 train_acc= 0.52364 val_loss= 1.05799 val_acc= 0.44262 time= 0.01563
Epoch: 0006 train_loss= 0.94815 train_acc= 0.53455 val_loss= 0.96217 val_acc= 0.44262 time= 0.04014
Epoch: 0007 train_loss= 1.50158 train_acc= 0.52545 val_loss= 0.82381 val_acc= 0.42623 time= 0.03125
Epoch: 0008 train_loss= 0.78903 train_acc= 0.50364 val_loss= 0.76967 val_acc= 0.40984 time= 0.03125
Epoch: 0009 train_loss= 0.74421 train_acc= 0.46364 val_loss= 0.75902 val_acc= 0.44262 time= 0.03125
Epoch: 0010 train_loss= 0.96147 train_acc= 0.53818 val_loss= 0.77747 val_acc= 0.57377 time= 0.03125
Epoch: 0011 train_loss= 0.74308 train_acc= 0.50909 val_loss= 0.79004 val_acc= 0.57377 time= 0.01563
Epoch: 0012 train_loss= 0.72633 train_acc= 0.52000 val_loss= 0.79829 val_acc= 0.57377 time= 0.03125
Epoch: 0013 train_loss= 0.77827 train_acc= 0.52909 val_loss= 0.79234 val_acc= 0.57377 time= 0.03125
Epoch: 0014 train_loss= 0.82325 train_acc= 0.49636 val_loss= 0.77428 val_acc= 0.55738 time= 0.01563
Epoch: 0015 train_loss= 0.76315 train_acc= 0.48545 val_loss= 0.75464 val_acc= 0.55738 time= 0.03125
Epoch: 0016 train_loss= 0.74696 train_acc= 0.50182 val_loss= 0.73812 val_acc= 0.55738 time= 0.03125
Epoch: 0017 train_loss= 0.91550 train_acc= 0.46909 val_loss= 0.72547 val_acc= 0.54098 time= 0.01563
Epoch: 0018 train_loss= 0.77164 train_acc= 0.49091 val_loss= 0.71783 val_acc= 0.50820 time= 0.03125
Epoch: 0019 train_loss= 0.71072 train_acc= 0.52182 val_loss= 0.71628 val_acc= 0.47541 time= 0.01563
Epoch: 0020 train_loss= 0.73576 train_acc= 0.55091 val_loss= 0.71867 val_acc= 0.49180 time= 0.01562
Epoch: 0021 train_loss= 0.73744 train_acc= 0.49091 val_loss= 0.72111 val_acc= 0.47541 time= 0.03125
Epoch: 0022 train_loss= 0.71321 train_acc= 0.49091 val_loss= 0.72344 val_acc= 0.40984 time= 0.01563
Epoch: 0023 train_loss= 0.70706 train_acc= 0.47636 val_loss= 0.72593 val_acc= 0.45902 time= 0.03125
Epoch: 0024 train_loss= 0.69935 train_acc= 0.51091 val_loss= 0.72861 val_acc= 0.44262 time= 0.03125
Epoch: 0025 train_loss= 0.71228 train_acc= 0.54545 val_loss= 0.72799 val_acc= 0.45902 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 0.71789 accuracy= 0.48361 time= 0.01563 
