# 34th place solution: Key points

Thanks to the Coleridge Initiative and to Kaggle for organizing such an exciting competition. Congratulations to all the winners!
My solution was based on the BERT MLM model published by
[@tungmphung](https://www.kaggle.com/tungmphung)
early on in the competition. It is referenced on the leaderboard.
It survived the leaderboard shakeup at the end (moved up 25 places).
All datasets / pre-trained models used were made public before the competition deadline as stipulated.
I was impacted by the 9 hour kernel training time limit. If I could circumvent this in some way, I would have gained further (more training epochs, more realistic model).
I used the external datasets published by
[@mlconsult](https://www.kaggle.com/mlconsult)
It improved my public score dramatically and had no adverse impact on my private score. I verified this by choosing 1 submission with this data included and 1 without, for my 2 final submissions and results were almost the same (0.372 and 0.373).
I look forward to continuing to be a part of this initiative. Thanks much!!