Seems like the overall_recall score has been removed from the evaluation metric. Is this some error or only the overall_accuracy is going to be the sole metric to determine the results?
With just a few days remaining for the challenge to end, I would request you to please confirm what exactly is going to be the metric.
Apart from that, it would be great if we could have a leaderboard of sorts so that we know where we lie exactly and modify our approach accordingly.