Epoch: 0001 train_loss= 2.08671 train_acc= 0.11950 val_loss= 2.08664 val_acc= 0.13793 time= 0.09376
Epoch: 0002 train_loss= 2.08507 train_acc= 0.11950 val_loss= 2.08468 val_acc= 0.13793 time= 0.01562
Epoch: 0003 train_loss= 2.08347 train_acc= 0.11950 val_loss= 2.08243 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.08191 train_acc= 0.11950 val_loss= 2.07998 val_acc= 0.13793 time= 0.01563
Epoch: 0005 train_loss= 2.08053 train_acc= 0.11950 val_loss= 2.07755 val_acc= 0.13793 time= 0.00000
Epoch: 0006 train_loss= 2.07935 train_acc= 0.08176 val_loss= 2.07527 val_acc= 0.10345 time= 0.01563
Epoch: 0007 train_loss= 2.07711 train_acc= 0.14465 val_loss= 2.07305 val_acc= 0.10345 time= 0.01563
Epoch: 0008 train_loss= 2.07630 train_acc= 0.13836 val_loss= 2.07070 val_acc= 0.10345 time= 0.00000
Epoch: 0009 train_loss= 2.07419 train_acc= 0.15094 val_loss= 2.06820 val_acc= 0.24138 time= 0.01563
Epoch: 0010 train_loss= 2.07340 train_acc= 0.14465 val_loss= 2.06560 val_acc= 0.24138 time= 0.00000
Epoch: 0011 train_loss= 2.07146 train_acc= 0.17610 val_loss= 2.06289 val_acc= 0.24138 time= 0.01563
Epoch: 0012 train_loss= 2.06927 train_acc= 0.18239 val_loss= 2.06008 val_acc= 0.24138 time= 0.01563
Epoch: 0013 train_loss= 2.06897 train_acc= 0.17610 val_loss= 2.05718 val_acc= 0.24138 time= 0.00000
Epoch: 0014 train_loss= 2.06830 train_acc= 0.12579 val_loss= 2.05426 val_acc= 0.24138 time= 0.01563
Epoch: 0015 train_loss= 2.06644 train_acc= 0.14465 val_loss= 2.05121 val_acc= 0.24138 time= 0.00000
Epoch: 0016 train_loss= 2.06500 train_acc= 0.16981 val_loss= 2.04809 val_acc= 0.24138 time= 0.00000
Epoch: 0017 train_loss= 2.06462 train_acc= 0.15723 val_loss= 2.04498 val_acc= 0.24138 time= 0.01563
Epoch: 0018 train_loss= 2.06261 train_acc= 0.16352 val_loss= 2.04205 val_acc= 0.24138 time= 0.00000
Epoch: 0019 train_loss= 2.06374 train_acc= 0.16352 val_loss= 2.03929 val_acc= 0.24138 time= 0.01563
Epoch: 0020 train_loss= 2.06306 train_acc= 0.15723 val_loss= 2.03691 val_acc= 0.24138 time= 0.01563
Epoch: 0021 train_loss= 2.06242 train_acc= 0.16352 val_loss= 2.03469 val_acc= 0.24138 time= 0.00000
Epoch: 0022 train_loss= 2.06120 train_acc= 0.16981 val_loss= 2.03268 val_acc= 0.24138 time= 0.01563
Epoch: 0023 train_loss= 2.06228 train_acc= 0.16981 val_loss= 2.03083 val_acc= 0.24138 time= 0.00000
Epoch: 0024 train_loss= 2.06175 train_acc= 0.16352 val_loss= 2.02939 val_acc= 0.24138 time= 0.01563
Epoch: 0025 train_loss= 2.06282 train_acc= 0.15094 val_loss= 2.02845 val_acc= 0.24138 time= 0.01563
Epoch: 0026 train_loss= 2.06144 train_acc= 0.16981 val_loss= 2.02820 val_acc= 0.24138 time= 0.00000
Epoch: 0027 train_loss= 2.06102 train_acc= 0.16981 val_loss= 2.02839 val_acc= 0.24138 time= 0.01562
Epoch: 0028 train_loss= 2.06059 train_acc= 0.18868 val_loss= 2.02869 val_acc= 0.24138 time= 0.00000
Epoch: 0029 train_loss= 2.06137 train_acc= 0.17610 val_loss= 2.02916 val_acc= 0.24138 time= 0.01563
Epoch: 0030 train_loss= 2.06084 train_acc= 0.15094 val_loss= 2.03003 val_acc= 0.24138 time= 0.01563
Epoch: 0031 train_loss= 2.05953 train_acc= 0.15094 val_loss= 2.03101 val_acc= 0.24138 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.06677 accuracy= 0.13559 time= 0.00000 
