Epoch: 0001 train_loss= 1.39376 train_acc= 0.19922 val_loss= 1.39374 val_acc= 0.30357 time= 0.35416
Epoch: 0002 train_loss= 1.39216 train_acc= 0.29102 val_loss= 1.39064 val_acc= 0.30357 time= 0.01500
Epoch: 0003 train_loss= 1.39061 train_acc= 0.31055 val_loss= 1.38860 val_acc= 0.30357 time= 0.01500
Epoch: 0004 train_loss= 1.38941 train_acc= 0.31055 val_loss= 1.38709 val_acc= 0.30357 time= 0.01600
Epoch: 0005 train_loss= 1.38837 train_acc= 0.30664 val_loss= 1.38570 val_acc= 0.30357 time= 0.01600
Epoch: 0006 train_loss= 1.38750 train_acc= 0.31055 val_loss= 1.38437 val_acc= 0.30357 time= 0.01400
Epoch: 0007 train_loss= 1.38677 train_acc= 0.31250 val_loss= 1.38311 val_acc= 0.30357 time= 0.01600
Epoch: 0008 train_loss= 1.38554 train_acc= 0.31250 val_loss= 1.38202 val_acc= 0.30357 time= 0.01500
Epoch: 0009 train_loss= 1.38441 train_acc= 0.31055 val_loss= 1.38096 val_acc= 0.30357 time= 0.01500
Epoch: 0010 train_loss= 1.38400 train_acc= 0.30664 val_loss= 1.37999 val_acc= 0.30357 time= 0.01600
Epoch: 0011 train_loss= 1.38292 train_acc= 0.30664 val_loss= 1.37902 val_acc= 0.30357 time= 0.01800
Epoch: 0012 train_loss= 1.38292 train_acc= 0.31055 val_loss= 1.37812 val_acc= 0.30357 time= 0.01600
Epoch: 0013 train_loss= 1.38079 train_acc= 0.31055 val_loss= 1.37743 val_acc= 0.30357 time= 0.01615
Epoch: 0014 train_loss= 1.38046 train_acc= 0.31055 val_loss= 1.37677 val_acc= 0.30357 time= 0.01716
Epoch: 0015 train_loss= 1.37924 train_acc= 0.30859 val_loss= 1.37614 val_acc= 0.30357 time= 0.01610
Epoch: 0016 train_loss= 1.37924 train_acc= 0.31055 val_loss= 1.37549 val_acc= 0.30357 time= 0.01700
Epoch: 0017 train_loss= 1.37854 train_acc= 0.31055 val_loss= 1.37463 val_acc= 0.30357 time= 0.03844
Epoch: 0018 train_loss= 1.37899 train_acc= 0.31055 val_loss= 1.37373 val_acc= 0.30357 time= 0.01632
Epoch: 0019 train_loss= 1.37859 train_acc= 0.31055 val_loss= 1.37291 val_acc= 0.30357 time= 0.01412
Epoch: 0020 train_loss= 1.37763 train_acc= 0.31055 val_loss= 1.37216 val_acc= 0.30357 time= 0.01400
Epoch: 0021 train_loss= 1.37930 train_acc= 0.30859 val_loss= 1.37158 val_acc= 0.30357 time= 0.01300
Epoch: 0022 train_loss= 1.37702 train_acc= 0.31250 val_loss= 1.37100 val_acc= 0.30357 time= 0.01600
Epoch: 0023 train_loss= 1.37798 train_acc= 0.30859 val_loss= 1.37051 val_acc= 0.30357 time= 0.01500
Epoch: 0024 train_loss= 1.37816 train_acc= 0.30859 val_loss= 1.37014 val_acc= 0.30357 time= 0.01600
Epoch: 0025 train_loss= 1.37912 train_acc= 0.31055 val_loss= 1.36975 val_acc= 0.30357 time= 0.01800
Epoch: 0026 train_loss= 1.37978 train_acc= 0.31055 val_loss= 1.36949 val_acc= 0.30357 time= 0.01600
Epoch: 0027 train_loss= 1.37880 train_acc= 0.30859 val_loss= 1.36947 val_acc= 0.30357 time= 0.01523
Epoch: 0028 train_loss= 1.37629 train_acc= 0.30859 val_loss= 1.36936 val_acc= 0.30357 time= 0.01339
Epoch: 0029 train_loss= 1.37813 train_acc= 0.31055 val_loss= 1.36943 val_acc= 0.30357 time= 0.01400
Epoch: 0030 train_loss= 1.37759 train_acc= 0.30859 val_loss= 1.36963 val_acc= 0.30357 time= 0.01300
Epoch: 0031 train_loss= 1.37831 train_acc= 0.31055 val_loss= 1.36990 val_acc= 0.30357 time= 0.01300
Epoch: 0032 train_loss= 1.37700 train_acc= 0.30859 val_loss= 1.37019 val_acc= 0.30357 time= 0.01405
Early stopping...
Optimization Finished!
Test set results: cost= 1.37089 accuracy= 0.29204 time= 0.00700 
