Introduce new scoring APIs for curation + training#88
Merged
Conversation
Signed-off-by: SumanthRH <sumanthrh@anyscale.com>
Signed-off-by: SumanthRH <sumanthrh@anyscale.com>
Signed-off-by: SumanthRH <sumanthrh@anyscale.com>
Signed-off-by: SumanthRH <sumanthrh@anyscale.com>
Signed-off-by: SumanthRH <sumanthrh@anyscale.com>
Signed-off-by: SumanthRH <sumanthrh@anyscale.com>
Signed-off-by: SumanthRH <sumanthrh@anyscale.com>
Signed-off-by: SumanthRH <sumanthrh@anyscale.com>
SumanthRH
commented
Feb 28, 2025
recipes/sky-t1-preview/recipe.py
Outdated
Comment on lines
38
to
41
| # We explicitly set the target number of blocks to help tune performance. | ||
| # For materialized datasets, the number of blocks determined by ray data can be small, | ||
| # especially for a multi-stage pipeline like the one here. | ||
| TARGET_NUM_ROWS_PER_BLOCK = 100 |
Member
Author
There was a problem hiding this comment.
I'm still tuning settings like these for performance
SumanthRH
commented
Feb 28, 2025
| @timeout(5) # Add timeout of 5 seconds | ||
| def check_correctness(self, problem, generation): | ||
| solution = extract_answer(problem[self.task_config.answer_key]) | ||
| solution = strip_answer_string(solution) |
Member
Author
There was a problem hiding this comment.
not needed because strip_answer_string is already called in extract_answer
SumanthRH
commented
Feb 28, 2025
| return dataset.iloc[start:end] if end > 0 else dataset.iloc[start:] | ||
|
|
||
|
|
||
| def _temp_run(problem, generation, debug, result): |
Member
Author
There was a problem hiding this comment.
Placed outside to solve the same issue as in #89
Signed-off-by: SumanthRH <sumanthrh@anyscale.com>
SumanthRH
commented
Feb 28, 2025
recipes/sky-t1-preview/recipe.py
Outdated
| numina_ds_olympiads = numina_ds_olympiads.limit(num_samples) | ||
| numina_ds_math = numina_ds_math.limit(num_samples) | ||
|
|
||
| # 2. Get model responses for each of the datasets |
SumanthRH
commented
Mar 1, 2025
|
|
||
| def convert_to_sharegpt_format(row: Dict[str, Any], prompt_column, response_column): | ||
| prompt = row[prompt_column] | ||
| # accept |
Signed-off-by: SumanthRH <sumanthrh@anyscale.com>
SumanthRH
commented
Mar 11, 2025
Member
Author
There was a problem hiding this comment.
Will move the actual example to a config file once other tests also make it in. Currently there's only one test so having all the context in one place is good
erictang000
reviewed
Mar 12, 2025
| backend: The backend to use for scoring. Supports "ray" or "mp" (str). | ||
| """ | ||
|
|
||
| TIMEOUT = 6 |
Collaborator
There was a problem hiding this comment.
just wondering how did you pick this value (6 here and 10 for apps)?
Member
Author
There was a problem hiding this comment.
the timeout value is actually from the original source code for the datasets.
erictang000
approved these changes
Mar 12, 2025
| backend: The backend to use for scoring. Supports "ray" or "mp" (str). | ||
| """ | ||
|
|
||
| TIMEOUT = 6 |
Collaborator
There was a problem hiding this comment.
also should this be a class constant or could it make sense for this to be a user configurable parameter passed into the constructor?
| @@ -0,0 +1,272 @@ | |||
| """ | |||
| This is the recipe for data curation for the Sky T1 Preview model . | |||
Collaborator
There was a problem hiding this comment.
Suggested change
| This is the recipe for data curation for the Sky T1 Preview model . | |
| This is the recipe for data curation for the Sky T1 Preview model. |
recipes/sky-t1-preview/recipe.py
Outdated
|
|
||
| config = vLLMEngineProcessorConfig( | ||
| model="Qwen/QwQ-32B-Preview", | ||
| # model="Qwen/Qwen2-0.5B-Instruct", |
Member
Author
There was a problem hiding this comment.
Yes will do. recipe.py is still under construction.
Signed-off-by: SumanthRH <sumanthrh@anyscale.com>
yllkryeziu
pushed a commit
to yllkryeziu/adaptive-compute-rewrite
that referenced
this pull request
Dec 12, 2025
PR to introduce the new scoring APIs to be shared between evaluation + curation + training. Also adds an example for using this with the new ray.data.llm APIs: docs.ray.io/en/master/data/working-with-llms.html using Sky-T1-32B-Preview data curation. The recipe is still WIP and has some rough edges on the original training dataset size, which will be fixed in a follow-up PR.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
What does this PR do?
WIP PR to introduce the new scoring APIs to be shared between evaluation + curation + training.
Also adds an example for using this with the new
ray.data.llmAPIs: docs.ray.io/en/master/data/working-with-llms.html using Sky-T1-32B-Preview data curation.TODO: