Epoch: 0001 train_loss= 2.08468 train_acc= 0.12579 val_loss= 2.08067 val_acc= 0.17241 time= 0.14063
Epoch: 0002 train_loss= 2.08292 train_acc= 0.14465 val_loss= 2.07866 val_acc= 0.27586 time= 0.01563
Epoch: 0003 train_loss= 2.08117 train_acc= 0.17610 val_loss= 2.07636 val_acc= 0.27586 time= 0.01563
Epoch: 0004 train_loss= 2.07863 train_acc= 0.17610 val_loss= 2.07376 val_acc= 0.27586 time= 0.01563
Epoch: 0005 train_loss= 2.07642 train_acc= 0.17610 val_loss= 2.07096 val_acc= 0.27586 time= 0.01563
Epoch: 0006 train_loss= 2.07513 train_acc= 0.18239 val_loss= 2.06805 val_acc= 0.27586 time= 0.01563
Epoch: 0007 train_loss= 2.07266 train_acc= 0.15723 val_loss= 2.06500 val_acc= 0.27586 time= 0.00000
Epoch: 0008 train_loss= 2.07198 train_acc= 0.15094 val_loss= 2.06157 val_acc= 0.27586 time= 0.01563
Epoch: 0009 train_loss= 2.06652 train_acc= 0.16981 val_loss= 2.05798 val_acc= 0.27586 time= 0.01563
Epoch: 0010 train_loss= 2.06834 train_acc= 0.13836 val_loss= 2.05437 val_acc= 0.27586 time= 0.01563
Epoch: 0011 train_loss= 2.06550 train_acc= 0.15094 val_loss= 2.05083 val_acc= 0.27586 time= 0.01563
Epoch: 0012 train_loss= 2.06026 train_acc= 0.17610 val_loss= 2.04741 val_acc= 0.27586 time= 0.00000
Epoch: 0013 train_loss= 2.05958 train_acc= 0.18239 val_loss= 2.04419 val_acc= 0.27586 time= 0.01563
Epoch: 0014 train_loss= 2.06012 train_acc= 0.16981 val_loss= 2.04128 val_acc= 0.27586 time= 0.01562
Epoch: 0015 train_loss= 2.05998 train_acc= 0.15723 val_loss= 2.03879 val_acc= 0.27586 time= 0.00000
Epoch: 0016 train_loss= 2.05787 train_acc= 0.16352 val_loss= 2.03665 val_acc= 0.27586 time= 0.01563
Epoch: 0017 train_loss= 2.05565 train_acc= 0.15723 val_loss= 2.03476 val_acc= 0.27586 time= 0.01563
Epoch: 0018 train_loss= 2.05635 train_acc= 0.16981 val_loss= 2.03314 val_acc= 0.27586 time= 0.00000
Epoch: 0019 train_loss= 2.05430 train_acc= 0.16981 val_loss= 2.03181 val_acc= 0.27586 time= 0.01563
Epoch: 0020 train_loss= 2.05301 train_acc= 0.16981 val_loss= 2.03068 val_acc= 0.27586 time= 0.00000
Epoch: 0021 train_loss= 2.05583 train_acc= 0.16981 val_loss= 2.02966 val_acc= 0.27586 time= 0.01563
Epoch: 0022 train_loss= 2.05818 train_acc= 0.16352 val_loss= 2.02883 val_acc= 0.27586 time= 0.01563
Epoch: 0023 train_loss= 2.05359 train_acc= 0.16981 val_loss= 2.02804 val_acc= 0.27586 time= 0.02008
Epoch: 0024 train_loss= 2.05383 train_acc= 0.16981 val_loss= 2.02724 val_acc= 0.27586 time= 0.01151
Epoch: 0025 train_loss= 2.05563 train_acc= 0.16352 val_loss= 2.02668 val_acc= 0.27586 time= 0.01563
Epoch: 0026 train_loss= 2.05613 train_acc= 0.16352 val_loss= 2.02616 val_acc= 0.27586 time= 0.00000
Epoch: 0027 train_loss= 2.05293 train_acc= 0.15723 val_loss= 2.02576 val_acc= 0.27586 time= 0.01563
Epoch: 0028 train_loss= 2.05197 train_acc= 0.16981 val_loss= 2.02526 val_acc= 0.27586 time= 0.01563
Epoch: 0029 train_loss= 2.05180 train_acc= 0.16981 val_loss= 2.02488 val_acc= 0.27586 time= 0.01563
Epoch: 0030 train_loss= 2.05329 train_acc= 0.16352 val_loss= 2.02446 val_acc= 0.27586 time= 0.00000
Epoch: 0031 train_loss= 2.04954 train_acc= 0.16981 val_loss= 2.02393 val_acc= 0.27586 time= 0.01563
Epoch: 0032 train_loss= 2.05275 train_acc= 0.17610 val_loss= 2.02340 val_acc= 0.27586 time= 0.01563
Epoch: 0033 train_loss= 2.05149 train_acc= 0.16981 val_loss= 2.02278 val_acc= 0.27586 time= 0.00000
Epoch: 0034 train_loss= 2.05104 train_acc= 0.16981 val_loss= 2.02211 val_acc= 0.27586 time= 0.01563
Epoch: 0035 train_loss= 2.05207 train_acc= 0.16352 val_loss= 2.02129 val_acc= 0.27586 time= 0.00000
Epoch: 0036 train_loss= 2.05492 train_acc= 0.16981 val_loss= 2.02045 val_acc= 0.27586 time= 0.01563
Epoch: 0037 train_loss= 2.05166 train_acc= 0.18239 val_loss= 2.01965 val_acc= 0.27586 time= 0.00000
Epoch: 0038 train_loss= 2.05102 train_acc= 0.16352 val_loss= 2.01886 val_acc= 0.27586 time= 0.01562
Epoch: 0039 train_loss= 2.05195 train_acc= 0.16981 val_loss= 2.01816 val_acc= 0.27586 time= 0.01563
Epoch: 0040 train_loss= 2.05223 train_acc= 0.16981 val_loss= 2.01753 val_acc= 0.27586 time= 0.00000
Epoch: 0041 train_loss= 2.05077 train_acc= 0.16352 val_loss= 2.01655 val_acc= 0.27586 time= 0.01563
Epoch: 0042 train_loss= 2.05169 train_acc= 0.15094 val_loss= 2.01575 val_acc= 0.27586 time= 0.00000
Epoch: 0043 train_loss= 2.05225 train_acc= 0.16981 val_loss= 2.01524 val_acc= 0.27586 time= 0.01563
Epoch: 0044 train_loss= 2.04717 train_acc= 0.17610 val_loss= 2.01514 val_acc= 0.27586 time= 0.00000
Epoch: 0045 train_loss= 2.04932 train_acc= 0.16981 val_loss= 2.01507 val_acc= 0.27586 time= 0.01562
Epoch: 0046 train_loss= 2.05119 train_acc= 0.16981 val_loss= 2.01512 val_acc= 0.27586 time= 0.00000
Epoch: 0047 train_loss= 2.05042 train_acc= 0.16981 val_loss= 2.01486 val_acc= 0.27586 time= 0.01563
Epoch: 0048 train_loss= 2.04922 train_acc= 0.16352 val_loss= 2.01455 val_acc= 0.27586 time= 0.01562
Epoch: 0049 train_loss= 2.04948 train_acc= 0.17610 val_loss= 2.01438 val_acc= 0.27586 time= 0.00000
Epoch: 0050 train_loss= 2.05194 train_acc= 0.16352 val_loss= 2.01433 val_acc= 0.27586 time= 0.01563
Epoch: 0051 train_loss= 2.04940 train_acc= 0.16981 val_loss= 2.01450 val_acc= 0.27586 time= 0.00000
Epoch: 0052 train_loss= 2.04925 train_acc= 0.16981 val_loss= 2.01471 val_acc= 0.27586 time= 0.01562
Epoch: 0053 train_loss= 2.05039 train_acc= 0.16981 val_loss= 2.01485 val_acc= 0.27586 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.07146 accuracy= 0.16949 time= 0.00000 
