Epoch: 0001 train_loss= 2.08704 train_acc= 0.15723 val_loss= 2.08255 val_acc= 0.27586 time= 0.15626
Epoch: 0002 train_loss= 2.08375 train_acc= 0.16981 val_loss= 2.07788 val_acc= 0.24138 time= 0.01562
Epoch: 0003 train_loss= 2.08067 train_acc= 0.15723 val_loss= 2.07319 val_acc= 0.24138 time= 0.00000
Epoch: 0004 train_loss= 2.07759 train_acc= 0.18868 val_loss= 2.06847 val_acc= 0.24138 time= 0.01562
Epoch: 0005 train_loss= 2.07543 train_acc= 0.16352 val_loss= 2.06396 val_acc= 0.27586 time= 0.01563
Epoch: 0006 train_loss= 2.07271 train_acc= 0.15723 val_loss= 2.05969 val_acc= 0.27586 time= 0.00000
Epoch: 0007 train_loss= 2.07066 train_acc= 0.16352 val_loss= 2.05547 val_acc= 0.27586 time= 0.01563
Epoch: 0008 train_loss= 2.06710 train_acc= 0.16981 val_loss= 2.05143 val_acc= 0.27586 time= 0.01563
Epoch: 0009 train_loss= 2.06535 train_acc= 0.16981 val_loss= 2.04765 val_acc= 0.27586 time= 0.00000
Epoch: 0010 train_loss= 2.06161 train_acc= 0.16352 val_loss= 2.04435 val_acc= 0.27586 time= 0.01563
Epoch: 0011 train_loss= 2.06147 train_acc= 0.16981 val_loss= 2.04160 val_acc= 0.27586 time= 0.01563
Epoch: 0012 train_loss= 2.05931 train_acc= 0.15094 val_loss= 2.03965 val_acc= 0.27586 time= 0.00000
Epoch: 0013 train_loss= 2.05748 train_acc= 0.15094 val_loss= 2.03848 val_acc= 0.27586 time= 0.01562
Epoch: 0014 train_loss= 2.05621 train_acc= 0.18239 val_loss= 2.03811 val_acc= 0.27586 time= 0.00000
Epoch: 0015 train_loss= 2.05542 train_acc= 0.17610 val_loss= 2.03847 val_acc= 0.06897 time= 0.01563
Epoch: 0016 train_loss= 2.05479 train_acc= 0.17610 val_loss= 2.03964 val_acc= 0.06897 time= 0.02015
Epoch: 0017 train_loss= 2.05346 train_acc= 0.19497 val_loss= 2.04139 val_acc= 0.06897 time= 0.01200
Epoch: 0018 train_loss= 2.05391 train_acc= 0.18239 val_loss= 2.04355 val_acc= 0.06897 time= 0.00105
Early stopping...
Optimization Finished!
Test set results: cost= 2.07386 accuracy= 0.11864 time= 0.00000 
