Dataset issues
#4
by
polymer
- opened
With some testing using the model, a peculiar issue was found where the model would sometimes output a closing brace (‘}’) after their turn. After looking through the dataset, it appears every conversation has the last turn ended by GPT with a closing brace appended at the end of its response.
For example (last turn, conversation ID AaatApy_0):
[ . . . { "from": "gpt", "value": "The impact of AI . . . opportunities in the years to come.}" } ]
Notice the brace that is erroneously placed inside the string. This issue is present for all conversations in the dataset.
Wow, thanks for the great feedback. We'll make sure to incorporate it in the next version. Thank you 🙏