Add retries to LM calls with LiteLLM #1718
Merged
Conversation
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
dbczumar
commented
Oct 29, 2024
| cache: bool = True, | ||
| launch_kwargs: Optional[Dict[str, Any]] = None, | ||
| callbacks: Optional[List[BaseCallback]] = None, | ||
| num_retries: int = 8, |
Collaborator
Author
There was a problem hiding this comment.
Empirically, 8 retries with exponential backoff in LiteLLM takes just over 1 minute with LiteLLM's builtin / default retry strategy. I defer to their exponential backoff retry strategy defaults, rather than defining our own (presumably, they know best)
dbczumar
commented
Oct 29, 2024
| temperature: float = 0.0, | ||
| max_tokens: int = 1000, | ||
| cache: bool = True, | ||
| launch_kwargs: Optional[Dict[str, Any]] = None, |
Collaborator
Author
There was a problem hiding this comment.
I didn't document this parameter because it's not actually used
dbczumar
commented
Oct 29, 2024
| cache_finetune=cache_finetune | ||
| ) | ||
| executor.submit(execute_finetune_job, finetune_job, lm=self, cache_finetune=cache_finetune) | ||
| executor.shutdown(wait=False) |
Collaborator
Author
There was a problem hiding this comment.
This is just linter formatting
dbczumar
commented
Oct 29, 2024
Comment on lines
-107
to
-113
| self, | ||
| train_data: List[Dict[str, Any]], | ||
| train_kwargs: Optional[Dict[str, Any]]=None, | ||
| train_method: TrainingMethod = TrainingMethod.SFT, | ||
| provider: str = "openai", | ||
| cache_finetune: bool = True, | ||
| ) -> FinetuneJob: |
Collaborator
Author
There was a problem hiding this comment.
This is just linter formatting
dbczumar
commented
Oct 29, 2024
Comment on lines
-14
to
-17
| from dspy.clients.lm_finetune_utils import ( | ||
| execute_finetune_job, | ||
| get_provider_finetune_job_class, | ||
| ) |
Collaborator
Author
There was a problem hiding this comment.
This is just linter formatting
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.
Add retries to LM calls with LiteLLM, and improve LM docstrings while we're here