Epoch: 0001 train_loss= 2.08747 train_acc= 0.06289 val_loss= 2.08512 val_acc= 0.03448 time= 0.17224
Epoch: 0002 train_loss= 2.08522 train_acc= 0.10692 val_loss= 2.08327 val_acc= 0.06897 time= 0.00000
Epoch: 0003 train_loss= 2.08328 train_acc= 0.13836 val_loss= 2.08165 val_acc= 0.06897 time= 0.01563
Epoch: 0004 train_loss= 2.08146 train_acc= 0.13836 val_loss= 2.08025 val_acc= 0.06897 time= 0.00000
Epoch: 0005 train_loss= 2.07982 train_acc= 0.14465 val_loss= 2.07911 val_acc= 0.06897 time= 0.01563
Epoch: 0006 train_loss= 2.07797 train_acc= 0.15723 val_loss= 2.07817 val_acc= 0.06897 time= 0.00000
Epoch: 0007 train_loss= 2.07694 train_acc= 0.15094 val_loss= 2.07743 val_acc= 0.06897 time= 0.01563
Epoch: 0008 train_loss= 2.07532 train_acc= 0.14465 val_loss= 2.07687 val_acc= 0.06897 time= 0.00000
Epoch: 0009 train_loss= 2.07329 train_acc= 0.15094 val_loss= 2.07641 val_acc= 0.06897 time= 0.00000
Epoch: 0010 train_loss= 2.07150 train_acc= 0.15094 val_loss= 2.07606 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.07058 train_acc= 0.15094 val_loss= 2.07598 val_acc= 0.06897 time= 0.00000
Epoch: 0012 train_loss= 2.06799 train_acc= 0.15094 val_loss= 2.07594 val_acc= 0.06897 time= 0.01563
Epoch: 0013 train_loss= 2.06686 train_acc= 0.15094 val_loss= 2.07612 val_acc= 0.06897 time= 0.00000
Epoch: 0014 train_loss= 2.06504 train_acc= 0.14465 val_loss= 2.07654 val_acc= 0.06897 time= 0.01563
Epoch: 0015 train_loss= 2.06420 train_acc= 0.15094 val_loss= 2.07709 val_acc= 0.06897 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08574 accuracy= 0.13559 time= 0.00000 
