Epoch: 0001 train_loss= 2.08712 train_acc= 0.12129 val_loss= 2.08374 val_acc= 0.03448 time= 0.35940
Epoch: 0002 train_loss= 2.08433 train_acc= 0.13747 val_loss= 2.08187 val_acc= 0.03448 time= 0.01562
Epoch: 0003 train_loss= 2.08205 train_acc= 0.11860 val_loss= 2.08044 val_acc= 0.17241 time= 0.00000
Epoch: 0004 train_loss= 2.07932 train_acc= 0.15633 val_loss= 2.07929 val_acc= 0.17241 time= 0.01563
Epoch: 0005 train_loss= 2.07747 train_acc= 0.15364 val_loss= 2.07860 val_acc= 0.17241 time= 0.00000
Epoch: 0006 train_loss= 2.07545 train_acc= 0.15633 val_loss= 2.07840 val_acc= 0.17241 time= 0.01563
Epoch: 0007 train_loss= 2.07390 train_acc= 0.15633 val_loss= 2.07863 val_acc= 0.17241 time= 0.01563
Epoch: 0008 train_loss= 2.07227 train_acc= 0.15364 val_loss= 2.07935 val_acc= 0.17241 time= 0.00000
Epoch: 0009 train_loss= 2.06996 train_acc= 0.15364 val_loss= 2.08051 val_acc= 0.17241 time= 0.01563
Epoch: 0010 train_loss= 2.06976 train_acc= 0.15633 val_loss= 2.08204 val_acc= 0.17241 time= 0.00000
Epoch: 0011 train_loss= 2.06772 train_acc= 0.15633 val_loss= 2.08398 val_acc= 0.17241 time= 0.01563
Epoch: 0012 train_loss= 2.06750 train_acc= 0.15364 val_loss= 2.08624 val_acc= 0.17241 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.06404 accuracy= 0.16949 time= 0.01563 
