Epoch: 0001 train_loss= 2.08705 train_acc= 0.10782 val_loss= 2.08414 val_acc= 0.13793 time= 0.76568
Epoch: 0002 train_loss= 2.08450 train_acc= 0.12399 val_loss= 2.08210 val_acc= 0.03448 time= 0.01563
Epoch: 0003 train_loss= 2.08212 train_acc= 0.14555 val_loss= 2.08039 val_acc= 0.03448 time= 0.00000
Epoch: 0004 train_loss= 2.08002 train_acc= 0.17790 val_loss= 2.07922 val_acc= 0.03448 time= 0.01562
Epoch: 0005 train_loss= 2.07835 train_acc= 0.17520 val_loss= 2.07849 val_acc= 0.03448 time= 0.00000
Epoch: 0006 train_loss= 2.07695 train_acc= 0.17520 val_loss= 2.07841 val_acc= 0.03448 time= 0.01563
Epoch: 0007 train_loss= 2.07501 train_acc= 0.17520 val_loss= 2.07866 val_acc= 0.03448 time= 0.00000
Epoch: 0008 train_loss= 2.07399 train_acc= 0.17520 val_loss= 2.07935 val_acc= 0.03448 time= 0.01563
Epoch: 0009 train_loss= 2.07293 train_acc= 0.17520 val_loss= 2.08044 val_acc= 0.03448 time= 0.00000
Epoch: 0010 train_loss= 2.07216 train_acc= 0.17520 val_loss= 2.08190 val_acc= 0.03448 time= 0.01563
Epoch: 0011 train_loss= 2.07120 train_acc= 0.17520 val_loss= 2.08349 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.07046 train_acc= 0.17520 val_loss= 2.08531 val_acc= 0.03448 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.07018 accuracy= 0.16949 time= 0.00000 
