Epoch: 0001 train_loss= 1.33979 train_acc= 0.51818 val_loss= 0.70717 val_acc= 0.55738 time= 0.15583
Epoch: 0002 train_loss= 1.02617 train_acc= 0.53939 val_loss= 0.71181 val_acc= 0.59016 time= 0.01562
Epoch: 0003 train_loss= 1.30328 train_acc= 0.47576 val_loss= 0.68452 val_acc= 0.57377 time= 0.00000
Epoch: 0004 train_loss= 1.09443 train_acc= 0.47879 val_loss= 0.72347 val_acc= 0.55738 time= 0.01563
Epoch: 0005 train_loss= 1.32563 train_acc= 0.47879 val_loss= 0.87944 val_acc= 0.49180 time= 0.01562
Epoch: 0006 train_loss= 1.49318 train_acc= 0.50303 val_loss= 0.98531 val_acc= 0.44262 time= 0.00000
Epoch: 0007 train_loss= 1.41355 train_acc= 0.50303 val_loss= 0.99791 val_acc= 0.44262 time= 0.01563
Epoch: 0008 train_loss= 1.08992 train_acc= 0.47879 val_loss= 1.03524 val_acc= 0.44262 time= 0.01563
Epoch: 0009 train_loss= 1.69055 train_acc= 0.50303 val_loss= 0.98346 val_acc= 0.45902 time= 0.01563
Epoch: 0010 train_loss= 1.14108 train_acc= 0.53636 val_loss= 0.90726 val_acc= 0.49180 time= 0.00000
Epoch: 0011 train_loss= 0.82164 train_acc= 0.52727 val_loss= 0.83895 val_acc= 0.42623 time= 0.01563
Epoch: 0012 train_loss= 0.93454 train_acc= 0.52424 val_loss= 0.80466 val_acc= 0.42623 time= 0.01563
Epoch: 0013 train_loss= 1.34559 train_acc= 0.51212 val_loss= 0.75629 val_acc= 0.40984 time= 0.01563
Epoch: 0014 train_loss= 1.13987 train_acc= 0.49697 val_loss= 0.72933 val_acc= 0.55738 time= 0.00000
Epoch: 0015 train_loss= 0.96890 train_acc= 0.53333 val_loss= 0.72593 val_acc= 0.50820 time= 0.01563
Epoch: 0016 train_loss= 1.04404 train_acc= 0.45758 val_loss= 0.72750 val_acc= 0.50820 time= 0.01563
Epoch: 0017 train_loss= 1.05172 train_acc= 0.46970 val_loss= 0.72424 val_acc= 0.52459 time= 0.00000
Epoch: 0018 train_loss= 0.79495 train_acc= 0.46667 val_loss= 0.72216 val_acc= 0.52459 time= 0.01563
Epoch: 0019 train_loss= 0.92987 train_acc= 0.50303 val_loss= 0.71775 val_acc= 0.55738 time= 0.01563
Epoch: 0020 train_loss= 0.82710 train_acc= 0.43939 val_loss= 0.71465 val_acc= 0.55738 time= 0.01894
Epoch: 0021 train_loss= 1.10392 train_acc= 0.53333 val_loss= 0.71301 val_acc= 0.55738 time= 0.00202
Epoch: 0022 train_loss= 1.46394 train_acc= 0.46364 val_loss= 0.71225 val_acc= 0.55738 time= 0.01050
Epoch: 0023 train_loss= 0.79087 train_acc= 0.51818 val_loss= 0.71721 val_acc= 0.54098 time= 0.01563
Epoch: 0024 train_loss= 0.72365 train_acc= 0.50303 val_loss= 0.72355 val_acc= 0.47541 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.71246 accuracy= 0.50000 time= 0.00000 
