Epoch: 0001 train_loss= 2.08276 train_acc= 0.18868 val_loss= 2.08281 val_acc= 0.13793 time= 0.07819
Epoch: 0002 train_loss= 2.08121 train_acc= 0.13836 val_loss= 2.08149 val_acc= 0.06897 time= 0.01562
Epoch: 0003 train_loss= 2.07885 train_acc= 0.15723 val_loss= 2.08046 val_acc= 0.06897 time= 0.00000
Epoch: 0004 train_loss= 2.07645 train_acc= 0.18239 val_loss= 2.07957 val_acc= 0.06897 time= 0.01563
Epoch: 0005 train_loss= 2.07462 train_acc= 0.18868 val_loss= 2.07907 val_acc= 0.06897 time= 0.00000
Epoch: 0006 train_loss= 2.07159 train_acc= 0.16352 val_loss= 2.07884 val_acc= 0.06897 time= 0.01563
Epoch: 0007 train_loss= 2.06954 train_acc= 0.16981 val_loss= 2.07888 val_acc= 0.13793 time= 0.00000
Epoch: 0008 train_loss= 2.06810 train_acc= 0.15094 val_loss= 2.07945 val_acc= 0.13793 time= 0.01563
Epoch: 0009 train_loss= 2.06672 train_acc= 0.17610 val_loss= 2.08047 val_acc= 0.06897 time= 0.00000
Epoch: 0010 train_loss= 2.06409 train_acc= 0.13836 val_loss= 2.08193 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.06090 train_acc= 0.15094 val_loss= 2.08382 val_acc= 0.06897 time= 0.01757
Epoch: 0012 train_loss= 2.06025 train_acc= 0.13836 val_loss= 2.08634 val_acc= 0.06897 time= 0.00303
Early stopping...
Optimization Finished!
Test set results: cost= 2.07960 accuracy= 0.10169 time= 0.00000 
