Error: GPT3 responding with finish_reason == None

General API discussion
1

Undefined behaviour from documentation and never seen before in the past, only appearing for davinci-003.

  • Appearing by chance (~1/5).
  • When returning None as the finish_reason, summary quality appeared to be normal.
  • Endpoint is competitions
  • Started to notice in the last hour.

Sample response when handling responses with openai python library:

“{‘choices’: [{‘finish_reason’: None, ‘index’: 0, ‘logprobs’: None, ‘text’: X(but normal)}], ‘created’: X, ‘id’: X, ‘model’: ‘text-davinci-003’, ‘object’: ‘text_completion’, ‘usage’: X}”

Is this a permanent change, openai error or model error? How should I handle this? (same as “stop”?)

1 Like
2

Is there a fast method of contacting openai support regarding this? (This is a clear sentence)

3

You can sometimes have luck on their Discord if you’re lucky and can navigate around amidst the flood of conversations going on.

Might be something new they’re testing… or a bug…

Is it affecting your code somehow?

4

Yeah, we don’t know how to handle/if we should handle the case where None is returned. Previously its just set to put anything other than “stop” to fail, but the summary quality of None seems fine…

1 Like
5

Yeah, the verbiage makes me think it’s temporary. Might add it into your whitelist, though, if it’s giving good completions… maybe with an extra warning to users?

Good luck!

6

Hi @guan

I always specify a stop (normally ####) and have only seen completions end for 1 of 2 reasons:

  1. ‘stop’
  2. ‘length’

Honest, I have never experienced any “None” reason for a finished completion and like you I mostly use the text-davinci-003 model.

If you have any specific prompt you have experienced issues with, please post the prompt (all your API completion parameters) and I will test it for you.

Please note that I can reproduce the “None” completion reason by including the stop in the prompt; so I recommend you only send the stop parameter to the API and do not include the stop in the actual prompt.

Hope this helps.

:slight_smile: