-
Notifications
You must be signed in to change notification settings - Fork 6
feat: Update SS with evals for Grade 5-12 #5
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
gary-mu
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Love this integration of grade 5-12.
2 comments:
- Can we also add Ariena as reviewer? She's not a member of this repo, so I can't add her
- Can we add test result? I think running test passages and paste result can be sufficient.
|
Overall LGTM. Two small callouts:
|
aychi1
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Overall LGTM. Commented on some non-blocking nits.
| " description=\"Max number of clauses (independent + subordinate) found in a single sentence.\"\n", | ||
| " )\n", | ||
| " # (Grades 5-12)\n", | ||
| " num_compound: int = Field(\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Just curious, is there a reason why we have both num_compound_sentences (line 173) and num_compound (line 259)? Asking bc I noticed that the definition is the same across both Grades 3-4 vs. 5-12 evals.
On a similar note, the definition for Simple Sentences is slightly different between Noah's prompt vs. Wayne's prompt. It likely does not make a big difference, but just want to call out that we've never tested.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think it might be good to keep the prompt for each version as untouched as possible as we know LLM output is sensitive to prompt changes.
This PR extends the Sentence Structure Evaluator (notebook) to support additional grades (5 to 12) beyond the existing grades (3 & 4).
Status: This PR is currently under internal review and testing, before it is ready to be released