Epoch: 0001 train_loss= 0.70101 train_acc= 0.52364 val_loss= 0.69831 val_acc= 0.42623 time= 0.23439
Epoch: 0002 train_loss= 0.69808 train_acc= 0.55091 val_loss= 0.69609 val_acc= 0.55738 time= 0.01563
Epoch: 0003 train_loss= 0.69600 train_acc= 0.60182 val_loss= 0.69467 val_acc= 0.59016 time= 0.01563
Epoch: 0004 train_loss= 0.69445 train_acc= 0.62909 val_loss= 0.69389 val_acc= 0.55738 time= 0.00000
Epoch: 0005 train_loss= 0.69358 train_acc= 0.67091 val_loss= 0.69390 val_acc= 0.44262 time= 0.01563
Epoch: 0006 train_loss= 0.69305 train_acc= 0.59091 val_loss= 0.69397 val_acc= 0.42623 time= 0.01563
Epoch: 0007 train_loss= 0.69282 train_acc= 0.64000 val_loss= 0.69419 val_acc= 0.42623 time= 0.00000
Epoch: 0008 train_loss= 0.69279 train_acc= 0.57273 val_loss= 0.69416 val_acc= 0.45902 time= 0.01563
Epoch: 0009 train_loss= 0.69259 train_acc= 0.56727 val_loss= 0.69386 val_acc= 0.52459 time= 0.01563
Epoch: 0010 train_loss= 0.69250 train_acc= 0.65091 val_loss= 0.69378 val_acc= 0.59016 time= 0.00000
Epoch: 0011 train_loss= 0.69262 train_acc= 0.62727 val_loss= 0.69364 val_acc= 0.60656 time= 0.01563
Epoch: 0012 train_loss= 0.69254 train_acc= 0.67455 val_loss= 0.69334 val_acc= 0.54098 time= 0.01563
Epoch: 0013 train_loss= 0.69225 train_acc= 0.66182 val_loss= 0.69328 val_acc= 0.55738 time= 0.00000
Epoch: 0014 train_loss= 0.69218 train_acc= 0.62364 val_loss= 0.69293 val_acc= 0.57377 time= 0.01563
Epoch: 0015 train_loss= 0.69211 train_acc= 0.67636 val_loss= 0.69278 val_acc= 0.57377 time= 0.01563
Epoch: 0016 train_loss= 0.69162 train_acc= 0.64909 val_loss= 0.69320 val_acc= 0.59016 time= 0.01563
Epoch: 0017 train_loss= 0.69169 train_acc= 0.60000 val_loss= 0.69301 val_acc= 0.59016 time= 0.00000
Epoch: 0018 train_loss= 0.69066 train_acc= 0.62364 val_loss= 0.69235 val_acc= 0.57377 time= 0.01563
Epoch: 0019 train_loss= 0.69148 train_acc= 0.64364 val_loss= 0.69231 val_acc= 0.57377 time= 0.01563
Epoch: 0020 train_loss= 0.69085 train_acc= 0.66000 val_loss= 0.69261 val_acc= 0.55738 time= 0.00000
Epoch: 0021 train_loss= 0.68993 train_acc= 0.64000 val_loss= 0.69273 val_acc= 0.60656 time= 0.01563
Epoch: 0022 train_loss= 0.69058 train_acc= 0.61091 val_loss= 0.69269 val_acc= 0.57377 time= 0.01563
Epoch: 0023 train_loss= 0.69045 train_acc= 0.61091 val_loss= 0.69238 val_acc= 0.57377 time= 0.01563
Epoch: 0024 train_loss= 0.68957 train_acc= 0.59636 val_loss= 0.69130 val_acc= 0.60656 time= 0.00000
Epoch: 0025 train_loss= 0.69039 train_acc= 0.64909 val_loss= 0.69112 val_acc= 0.65574 time= 0.01563
Epoch: 0026 train_loss= 0.69074 train_acc= 0.65091 val_loss= 0.69189 val_acc= 0.59016 time= 0.01563
Epoch: 0027 train_loss= 0.68996 train_acc= 0.62909 val_loss= 0.69346 val_acc= 0.55738 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69440 accuracy= 0.57377 time= 0.01563 
