-
Notifications
You must be signed in to change notification settings - Fork 2.6k
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
Andrew/evals refactor #579
Conversation
evals/elsuite/basic/fuzzy_match.py
Outdated
@@ -22,14 +23,15 @@ def __init__( | |||
def eval_sample(self, test_sample, rng): | |||
del rng | |||
prompt, correct_answers = test_sample["input"], test_sample["ideal"] | |||
response, actual_prompt, metadata = self._completion_fn( | |||
response = self._completion_fn( |
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.
nit: result
to be consistent
evals/elsuite/basic/includes.py
Outdated
@@ -22,17 +23,16 @@ def __init__( | |||
self._completion_fn = completion_fn | |||
|
|||
def eval_sample(self, sample: Any, *_): | |||
response, actual_prompt, metadata = self._completion_fn( | |||
response = self._completion_fn( |
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.
ditto
evals/api.py
Outdated
the approriate `Prompt` class. | ||
`kwargs`: Other arguments passed to the API. | ||
@abstractmethod | ||
def extract_completions(self) -> List[str]: |
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.
nit: let's be consistent with list
instead of List
evals/api.py
Outdated
def __init__(self, raw_data: Any, prompt: Any, metadata: Dict[str, Any] = None): | ||
self.raw_data = raw_data | ||
self.prompt: str = prompt | ||
self.completions: List[str] = self.extract_completions() |
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.
self.extract_completions()
is called twice, once in the constructor here and another in the eval classes (e.g. Match line 45.
I think we can make completion
or completions
a property of ReturnType
and the eval class just access them.
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 one comment, otherwise looks good!
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.
Looking much cleaner with splitting into OpenAICompletionFn and OpenAIChatCompletionFn
evals/api.py
Outdated
} | ||
|
||
sampled = result.get_completions()[0] | ||
record_sampling(prompt=result.prompt, sampled=sampled) |
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.
Should we leave it up to CompletionFn to record the sampling event? It might actually be better since sometimes there could be some implementation-specific information that we might want to record.
temperature: float = 1.0, | ||
top_p: float = 0.9, | ||
max_tokens: int = 512, | ||
stop: Optional[str] = None, | ||
n_samples: Optional[int] = None, | ||
return_logprobs: bool = False, | ||
**kwargs, | ||
) -> Union[str, list[str], dict]: | ||
""" |
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.
Remove return_logprobs
from ARGS list
- [evals] Refactor evals package to expose `completion_fn`. - Add `record_raw_samples` - Andrew/evals refactor (#579) - update manifest and pyproject to support fetching data on pip install (#592) - we need to still use the interop for string/list[dicts] for modelgraded evals - refactor simple evals to not use result.prompt (#593) - Clean up duplicate recordings - Replace ModelSpecs with CompletionFn (#594) - Add --registry_path CLI arg # Thank you for contributing an eval!♥️ 🚨 Please make sure your PR follows these guidelines, __failure to follow the guidelines below will result in the PR being closed automatically__. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨 __PLEASE READ THIS__: In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task. We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. We encourage partial PR's with ~5-10 example that we can then run the evals on and share the results with you so you know how your eval does with GPT-4 before writing all 100 examples. ## Eval details 📑 ### Eval name [Insert Eval name here] ### Eval description [Insert a short description of what your eval does here] ### What makes this a useful eval? [Insert why this eval is worth including and any additional context] ## Criteria for a good eval ✅ Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals). Your eval should be: - [ ] Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world. - [ ] Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not. - [ ] Includes good signal around what is the right behavior. This means either a correct answer for `Basic` evals or the `Fact` Model-graded eval, or an exhaustive rubric for evaluating answers for the `Criteria` Model-graded eval. - [ ] Include at least 100 high quality examples (it is okay to only contribute 5-10 meaningful examples and have us test them with GPT-4 before adding all 100) If there is anything else that makes your eval worth including, please document it below. ### Unique eval value > Insert what makes your eval high quality that was not mentioned above. (Not required) ## Eval structure 🏗️ Your eval should - [ ] Check that your data is in `evals/registry/data/{name}` - [ ] Check that your yaml is registered at `evals/registry/evals/{name}.yaml` - [ ] Ensure you have the right to use the data you submit via this eval (For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.) ## Final checklist 👀 ### Submission agreement By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies). - [ ] I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies. ### Email address validation If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request. - [ ] I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request. ### Limited availability acknowledgement We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR. - [ ] I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access granted. ### Submit eval - [ ] I have filled out all required fields in the evals PR form - [ ] (Ignore if not submitting code) I have run `pip install pre-commit; pre-commit install` and have verified that `black`, `isort`, and `autoflake` are running when I commit and push Failure to fill out all required fields will result in the PR being closed. ### Eval JSON data Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here: <details> <summary>View evals in JSON</summary> ### Eval ```jsonl INSERT_EVAL_HERE ``` </details>
Thank you for contributing an eval!♥️
🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨
PLEASE READ THIS:
In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task.
We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. We encourage partial PR's with ~5-10 example that we can then run the evals on and share the results with you so you know how your eval does with GPT-4 before writing all 100 examples.
Eval details 📑
Eval name
[Insert Eval name here]
Eval description
[Insert a short description of what your eval does here]
What makes this a useful eval?
[Insert why this eval is worth including and any additional context]
Criteria for a good eval ✅
Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals).
Your eval should be:
Basic
evals or theFact
Model-graded eval, or an exhaustive rubric for evaluating answers for theCriteria
Model-graded eval.If there is anything else that makes your eval worth including, please document it below.
Unique eval value
Eval structure 🏗️
Your eval should
evals/registry/data/{name}
evals/registry/evals/{name}.yaml
(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.)
Final checklist 👀
Submission agreement
By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).
Email address validation
If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request.
Limited availability acknowledgement
We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.
Submit eval
pip install pre-commit; pre-commit install
and have verified thatblack
,isort
, andautoflake
are running when I commit and pushFailure to fill out all required fields will result in the PR being closed.
Eval JSON data
Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here:
View evals in JSON
Eval
INSERT_EVAL_HERE