Data contamination with GSM8k?

#4
by kno10 - opened

https://huggingface.co/datasets/Intel/neural-chat-dataset-v2
which appears to be the latest Intel neuralchat data that I could find, contains
https://huggingface.co/datasets/TigerResearch/tigerbot-gsm-8k-en
which contains 8.79k rows, i.e., the full GSM 8k data set, including test.
This would explain the high performance in the GSM8k benchmark of the leaderboard.

Intel org

hi, this model didn't use the dataset https://huggingface.co/datasets/Intel/neural-chat-dataset-v2.

Thanks~

Sign up or log in to comment