Epoch: 0001 train_loss= 2.11457 train_acc= 0.10943 val_loss= 2.06967 val_acc= 0.17241 time= 0.48477
Epoch: 0002 train_loss= 2.10945 train_acc= 0.11321 val_loss= 2.07002 val_acc= 0.17241 time= 0.01562
Epoch: 0003 train_loss= 2.09947 train_acc= 0.11698 val_loss= 2.07027 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.09515 train_acc= 0.11698 val_loss= 2.07090 val_acc= 0.13793 time= 0.00000
Epoch: 0005 train_loss= 2.09180 train_acc= 0.12830 val_loss= 2.07166 val_acc= 0.13793 time= 0.01563
Epoch: 0006 train_loss= 2.08821 train_acc= 0.13208 val_loss= 2.07250 val_acc= 0.13793 time= 0.00000
Epoch: 0007 train_loss= 2.08342 train_acc= 0.13208 val_loss= 2.07327 val_acc= 0.13793 time= 0.00000
Epoch: 0008 train_loss= 2.08196 train_acc= 0.13208 val_loss= 2.07412 val_acc= 0.13793 time= 0.01563
Epoch: 0009 train_loss= 2.07979 train_acc= 0.13208 val_loss= 2.07506 val_acc= 0.13793 time= 0.00000
Epoch: 0010 train_loss= 2.07678 train_acc= 0.13208 val_loss= 2.07600 val_acc= 0.13793 time= 0.00000
Epoch: 0011 train_loss= 2.07467 train_acc= 0.12830 val_loss= 2.07689 val_acc= 0.13793 time= 0.01563
Epoch: 0012 train_loss= 2.07361 train_acc= 0.15094 val_loss= 2.07774 val_acc= 0.10345 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07532 accuracy= 0.11864 time= 0.00000 
