Epoch: 0001 train_loss= 1.39365 train_acc= 0.21229 val_loss= 1.39240 val_acc= 0.21429 time= 0.32815
Epoch: 0002 train_loss= 1.39186 train_acc= 0.25419 val_loss= 1.38939 val_acc= 0.41071 time= 0.01562
Epoch: 0003 train_loss= 1.39047 train_acc= 0.29749 val_loss= 1.38653 val_acc= 0.41071 time= 0.01563
Epoch: 0004 train_loss= 1.38912 train_acc= 0.30587 val_loss= 1.38430 val_acc= 0.41071 time= 0.01563
Epoch: 0005 train_loss= 1.38822 train_acc= 0.30587 val_loss= 1.38246 val_acc= 0.41071 time= 0.01563
Epoch: 0006 train_loss= 1.38716 train_acc= 0.30587 val_loss= 1.38056 val_acc= 0.41071 time= 0.01563
Epoch: 0007 train_loss= 1.38619 train_acc= 0.30587 val_loss= 1.37861 val_acc= 0.41071 time= 0.01563
Epoch: 0008 train_loss= 1.38560 train_acc= 0.30587 val_loss= 1.37662 val_acc= 0.41071 time= 0.01563
Epoch: 0009 train_loss= 1.38475 train_acc= 0.30587 val_loss= 1.37459 val_acc= 0.41071 time= 0.01563
Epoch: 0010 train_loss= 1.38378 train_acc= 0.30587 val_loss= 1.37249 val_acc= 0.41071 time= 0.01563
Epoch: 0011 train_loss= 1.38299 train_acc= 0.30587 val_loss= 1.37033 val_acc= 0.41071 time= 0.01563
Epoch: 0012 train_loss= 1.38234 train_acc= 0.30587 val_loss= 1.36812 val_acc= 0.41071 time= 0.01563
Epoch: 0013 train_loss= 1.38150 train_acc= 0.30587 val_loss= 1.36584 val_acc= 0.41071 time= 0.01563
Epoch: 0014 train_loss= 1.38101 train_acc= 0.30587 val_loss= 1.36351 val_acc= 0.41071 time= 0.01563
Epoch: 0015 train_loss= 1.38052 train_acc= 0.30587 val_loss= 1.36115 val_acc= 0.41071 time= 0.01563
Epoch: 0016 train_loss= 1.37926 train_acc= 0.30587 val_loss= 1.35878 val_acc= 0.41071 time= 0.01563
Epoch: 0017 train_loss= 1.37904 train_acc= 0.30587 val_loss= 1.35643 val_acc= 0.41071 time= 0.03125
Epoch: 0018 train_loss= 1.37853 train_acc= 0.30587 val_loss= 1.35411 val_acc= 0.41071 time= 0.01563
Epoch: 0019 train_loss= 1.37809 train_acc= 0.30587 val_loss= 1.35191 val_acc= 0.41071 time= 0.01562
Epoch: 0020 train_loss= 1.37731 train_acc= 0.30587 val_loss= 1.34986 val_acc= 0.41071 time= 0.01563
Epoch: 0021 train_loss= 1.37761 train_acc= 0.30587 val_loss= 1.34802 val_acc= 0.41071 time= 0.01563
Epoch: 0022 train_loss= 1.37650 train_acc= 0.30587 val_loss= 1.34640 val_acc= 0.41071 time= 0.01563
Epoch: 0023 train_loss= 1.37701 train_acc= 0.30587 val_loss= 1.34507 val_acc= 0.41071 time= 0.01563
Epoch: 0024 train_loss= 1.37647 train_acc= 0.30587 val_loss= 1.34409 val_acc= 0.41071 time= 0.01563
Epoch: 0025 train_loss= 1.37661 train_acc= 0.30587 val_loss= 1.34337 val_acc= 0.41071 time= 0.01563
Epoch: 0026 train_loss= 1.37571 train_acc= 0.30587 val_loss= 1.34291 val_acc= 0.41071 time= 0.01563
Epoch: 0027 train_loss= 1.37634 train_acc= 0.30587 val_loss= 1.34283 val_acc= 0.41071 time= 0.01563
Epoch: 0028 train_loss= 1.37614 train_acc= 0.30587 val_loss= 1.34298 val_acc= 0.41071 time= 0.01563
Epoch: 0029 train_loss= 1.37585 train_acc= 0.30587 val_loss= 1.34333 val_acc= 0.41071 time= 0.01563
Epoch: 0030 train_loss= 1.37571 train_acc= 0.30587 val_loss= 1.34374 val_acc= 0.41071 time= 0.01563
Epoch: 0031 train_loss= 1.37561 train_acc= 0.30587 val_loss= 1.34424 val_acc= 0.41071 time= 0.01563
Epoch: 0032 train_loss= 1.37565 train_acc= 0.30587 val_loss= 1.34472 val_acc= 0.41071 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37955 accuracy= 0.29204 time= 0.00000 
