Feature/track raw score #63
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
3 tasks
p-ferreira
reviewed
Nov 8, 2023
There was a problem hiding this comment.
What if we streamline the whole process into an abstraction where:
get_rewardsreturn aBaseRewardEvent,BaseRewardModel.applyreturns aBaseRewardEventBaseRewardEventhas the logic to convert it itself into a dictionary, from which we can spread its properties later in theforwardcall and in the event schema- Complement the event schema with the expected new fields
p-ferreira
reviewed
Nov 8, 2023
p-ferreira
approved these changes
Nov 8, 2023
steffencruz
reviewed
Nov 8, 2023
| with torch.no_grad(): | ||
| inputs = self.tokenizer(prompt, completion, return_tensors="pt").to( | ||
| self.device | ||
| ) | ||
| return float(self.model(**inputs).logits[0].cpu().detach()) | ||
| reward_event.reward = float(self.model(**inputs).logits[0].cpu().detach()) |
There was a problem hiding this comment.
shouldn't this be reward_event.score since its float? where is reward_event.reward:Bool?
There was a problem hiding this comment.
rlhf is a reward model (not filter model), so there is no bool reward, and the score = reward
Co-authored-by: Steffen Cruz <[email protected]>
Co-authored-by: Steffen Cruz <[email protected]>
Co-authored-by: Steffen Cruz <[email protected]>
Co-authored-by: Steffen Cruz <[email protected]>
Co-authored-by: Steffen Cruz <[email protected]>
Co-authored-by: Steffen Cruz <[email protected]>
Co-authored-by: Steffen Cruz <[email protected]>
Co-authored-by: Steffen Cruz <[email protected]>
…or/text-prompting into feature/track_raw_score
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.