Epoch: 0001 train_loss= 2.09584 train_acc= 0.12129 val_loss= 2.11254 val_acc= 0.13793 time= 0.90101
Epoch: 0002 train_loss= 2.10381 train_acc= 0.14286 val_loss= 2.10942 val_acc= 0.10345 time= 0.01600
Epoch: 0003 train_loss= 2.08875 train_acc= 0.11860 val_loss= 2.10411 val_acc= 0.10345 time= 0.01300
Epoch: 0004 train_loss= 2.07915 train_acc= 0.17251 val_loss= 2.09958 val_acc= 0.10345 time= 0.01600
Epoch: 0005 train_loss= 2.08586 train_acc= 0.15094 val_loss= 2.09326 val_acc= 0.10345 time= 0.01300
Epoch: 0006 train_loss= 2.07205 train_acc= 0.16712 val_loss= 2.08588 val_acc= 0.10345 time= 0.01500
Epoch: 0007 train_loss= 2.05896 train_acc= 0.16981 val_loss= 2.08152 val_acc= 0.10345 time= 0.01300
Epoch: 0008 train_loss= 2.07684 train_acc= 0.15903 val_loss= 2.07905 val_acc= 0.10345 time= 0.01500
Epoch: 0009 train_loss= 2.06210 train_acc= 0.17790 val_loss= 2.08028 val_acc= 0.13793 time= 0.01400
Epoch: 0010 train_loss= 2.04899 train_acc= 0.17520 val_loss= 2.08119 val_acc= 0.10345 time= 0.01500
Epoch: 0011 train_loss= 2.05613 train_acc= 0.15094 val_loss= 2.08237 val_acc= 0.10345 time= 0.01400
Epoch: 0012 train_loss= 2.04593 train_acc= 0.18059 val_loss= 2.08429 val_acc= 0.10345 time= 0.01500
Epoch: 0013 train_loss= 2.03254 train_acc= 0.18868 val_loss= 2.08669 val_acc= 0.13793 time= 0.01300
Epoch: 0014 train_loss= 2.03884 train_acc= 0.17520 val_loss= 2.08861 val_acc= 0.17241 time= 0.01375
Early stopping...
Optimization Finished!
Test set results: cost= 2.08933 accuracy= 0.15254 time= 0.00000 
