Epoch: 0001 train_loss= 2.09768 train_acc= 0.12129 val_loss= 2.08928 val_acc= 0.17241 time= 0.89068
Epoch: 0002 train_loss= 2.09374 train_acc= 0.13747 val_loss= 2.08646 val_acc= 0.03448 time= 0.00000
Epoch: 0003 train_loss= 2.08789 train_acc= 0.16442 val_loss= 2.08376 val_acc= 0.03448 time= 0.00000
Epoch: 0004 train_loss= 2.08448 train_acc= 0.14825 val_loss= 2.08140 val_acc= 0.03448 time= 0.01562
Epoch: 0005 train_loss= 2.07981 train_acc= 0.15364 val_loss= 2.07937 val_acc= 0.03448 time= 0.00000
Epoch: 0006 train_loss= 2.07822 train_acc= 0.15364 val_loss= 2.07773 val_acc= 0.03448 time= 0.00000
Epoch: 0007 train_loss= 2.07576 train_acc= 0.15633 val_loss= 2.07637 val_acc= 0.03448 time= 0.01563
Epoch: 0008 train_loss= 2.07323 train_acc= 0.15364 val_loss= 2.07511 val_acc= 0.03448 time= 0.00000
Epoch: 0009 train_loss= 2.07217 train_acc= 0.15633 val_loss= 2.07375 val_acc= 0.03448 time= 0.00000
Epoch: 0010 train_loss= 2.06948 train_acc= 0.16173 val_loss= 2.07266 val_acc= 0.03448 time= 0.01563
Epoch: 0011 train_loss= 2.06750 train_acc= 0.16173 val_loss= 2.07213 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.06546 train_acc= 0.15364 val_loss= 2.07150 val_acc= 0.03448 time= 0.00000
Epoch: 0013 train_loss= 2.06444 train_acc= 0.19946 val_loss= 2.07108 val_acc= 0.13793 time= 0.01563
Epoch: 0014 train_loss= 2.06173 train_acc= 0.18868 val_loss= 2.07103 val_acc= 0.13793 time= 0.00000
Epoch: 0015 train_loss= 2.06070 train_acc= 0.17251 val_loss= 2.07142 val_acc= 0.13793 time= 0.00000
Epoch: 0016 train_loss= 2.06147 train_acc= 0.16712 val_loss= 2.07187 val_acc= 0.13793 time= 0.01562
Epoch: 0017 train_loss= 2.06029 train_acc= 0.16173 val_loss= 2.07216 val_acc= 0.13793 time= 0.00000
Epoch: 0018 train_loss= 2.06209 train_acc= 0.16173 val_loss= 2.07228 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.04098 accuracy= 0.13559 time= 0.01563 
