Epoch: 0001 train_loss= 2.08507 train_acc= 0.14286 val_loss= 2.08671 val_acc= 0.13793 time= 0.31252
Epoch: 0002 train_loss= 2.08330 train_acc= 0.14286 val_loss= 2.08654 val_acc= 0.13793 time= 0.01563
Epoch: 0003 train_loss= 2.08130 train_acc= 0.14286 val_loss= 2.08650 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.07981 train_acc= 0.14286 val_loss= 2.08641 val_acc= 0.13793 time= 0.01563
Epoch: 0005 train_loss= 2.07826 train_acc= 0.14286 val_loss= 2.08592 val_acc= 0.13793 time= 0.01563
Epoch: 0006 train_loss= 2.07675 train_acc= 0.14286 val_loss= 2.08547 val_acc= 0.13793 time= 0.00000
Epoch: 0007 train_loss= 2.07442 train_acc= 0.14286 val_loss= 2.08526 val_acc= 0.13793 time= 0.01563
Epoch: 0008 train_loss= 2.07330 train_acc= 0.14286 val_loss= 2.08507 val_acc= 0.13793 time= 0.00000
Epoch: 0009 train_loss= 2.07292 train_acc= 0.14286 val_loss= 2.08489 val_acc= 0.13793 time= 0.01563
Epoch: 0010 train_loss= 2.07090 train_acc= 0.14286 val_loss= 2.08469 val_acc= 0.13793 time= 0.00000
Epoch: 0011 train_loss= 2.06910 train_acc= 0.14286 val_loss= 2.08452 val_acc= 0.13793 time= 0.01563
Epoch: 0012 train_loss= 2.06850 train_acc= 0.14286 val_loss= 2.08430 val_acc= 0.13793 time= 0.01563
Epoch: 0013 train_loss= 2.06735 train_acc= 0.14016 val_loss= 2.08399 val_acc= 0.13793 time= 0.00000
Epoch: 0014 train_loss= 2.06546 train_acc= 0.14286 val_loss= 2.08359 val_acc= 0.13793 time= 0.01563
Epoch: 0015 train_loss= 2.06626 train_acc= 0.14555 val_loss= 2.08296 val_acc= 0.06897 time= 0.00000
Epoch: 0016 train_loss= 2.06387 train_acc= 0.15094 val_loss= 2.08222 val_acc= 0.06897 time= 0.01563
Epoch: 0017 train_loss= 2.06384 train_acc= 0.18598 val_loss= 2.08134 val_acc= 0.06897 time= 0.01563
Epoch: 0018 train_loss= 2.06348 train_acc= 0.17520 val_loss= 2.08020 val_acc= 0.06897 time= 0.00000
Epoch: 0019 train_loss= 2.06223 train_acc= 0.17790 val_loss= 2.07884 val_acc= 0.06897 time= 0.01563
Epoch: 0020 train_loss= 2.06102 train_acc= 0.17790 val_loss= 2.07735 val_acc= 0.06897 time= 0.00000
Epoch: 0021 train_loss= 2.06176 train_acc= 0.17790 val_loss= 2.07561 val_acc= 0.06897 time= 0.01563
Epoch: 0022 train_loss= 2.06030 train_acc= 0.17790 val_loss= 2.07373 val_acc= 0.06897 time= 0.01562
Epoch: 0023 train_loss= 2.06064 train_acc= 0.17790 val_loss= 2.07173 val_acc= 0.06897 time= 0.00000
Epoch: 0024 train_loss= 2.05911 train_acc= 0.17790 val_loss= 2.06968 val_acc= 0.06897 time= 0.01563
Epoch: 0025 train_loss= 2.05827 train_acc= 0.17790 val_loss= 2.06765 val_acc= 0.06897 time= 0.00000
Epoch: 0026 train_loss= 2.05952 train_acc= 0.17790 val_loss= 2.06567 val_acc= 0.06897 time= 0.01563
Epoch: 0027 train_loss= 2.05977 train_acc= 0.17790 val_loss= 2.06372 val_acc= 0.06897 time= 0.00000
Epoch: 0028 train_loss= 2.05831 train_acc= 0.17790 val_loss= 2.06181 val_acc= 0.06897 time= 0.01563
Epoch: 0029 train_loss= 2.05797 train_acc= 0.17790 val_loss= 2.06004 val_acc= 0.06897 time= 0.01563
Epoch: 0030 train_loss= 2.05719 train_acc= 0.17790 val_loss= 2.05851 val_acc= 0.06897 time= 0.00000
Epoch: 0031 train_loss= 2.05738 train_acc= 0.17790 val_loss= 2.05712 val_acc= 0.06897 time= 0.01563
Epoch: 0032 train_loss= 2.05804 train_acc= 0.17790 val_loss= 2.05590 val_acc= 0.06897 time= 0.00000
Epoch: 0033 train_loss= 2.05705 train_acc= 0.17790 val_loss= 2.05481 val_acc= 0.06897 time= 0.01563
Epoch: 0034 train_loss= 2.05723 train_acc= 0.17790 val_loss= 2.05373 val_acc= 0.06897 time= 0.01563
Epoch: 0035 train_loss= 2.05693 train_acc= 0.17790 val_loss= 2.05294 val_acc= 0.06897 time= 0.00000
Epoch: 0036 train_loss= 2.05538 train_acc= 0.17790 val_loss= 2.05215 val_acc= 0.06897 time= 0.01563
Epoch: 0037 train_loss= 2.05691 train_acc= 0.17790 val_loss= 2.05142 val_acc= 0.06897 time= 0.00000
Epoch: 0038 train_loss= 2.05671 train_acc= 0.18059 val_loss= 2.05097 val_acc= 0.06897 time= 0.01563
Epoch: 0039 train_loss= 2.05696 train_acc= 0.17790 val_loss= 2.05049 val_acc= 0.06897 time= 0.01563
Epoch: 0040 train_loss= 2.05598 train_acc= 0.17790 val_loss= 2.05032 val_acc= 0.06897 time= 0.00000
Epoch: 0041 train_loss= 2.05657 train_acc= 0.17790 val_loss= 2.05042 val_acc= 0.06897 time= 0.01563
Epoch: 0042 train_loss= 2.05510 train_acc= 0.18059 val_loss= 2.05069 val_acc= 0.06897 time= 0.00000
Epoch: 0043 train_loss= 2.05599 train_acc= 0.18059 val_loss= 2.05107 val_acc= 0.06897 time= 0.01563
Epoch: 0044 train_loss= 2.05637 train_acc= 0.17790 val_loss= 2.05132 val_acc= 0.06897 time= 0.00000
Epoch: 0045 train_loss= 2.05703 train_acc= 0.17520 val_loss= 2.05154 val_acc= 0.06897 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.06575 accuracy= 0.15254 time= 0.00000 
