Integrate benchmark and sampler #490
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
While writing this I made the following changes: * benchmark_repos was made a subdir of benchmarks so verify functions could import from generated code. Otherwise python complains it isn't part of a module. * In fact setup_repo does change the current directory. evalute_py and evaluate_sample now change the directory back. * The whole functions have a try now so spurious errors won't crash a run.
jakethekoenig
approved these changes
Jan 18, 2024
benchmarks/benchmark_runner.py
Outdated
| @@ -1,3 +1,5 @@ | |||
| from __future__ import annotations | |||
|
|
|||
| #!/usr/bin/env python | |||
There was a problem hiding this comment.
This line needs to be on top to allow this to be run as a script. e.g. got ./benchmarks/benchmark_runner.py to work instead of requiring python ./benchmarks/benchmark_runner.py
benchmarks/benchmark_runner.py
Outdated
|
|
||
| print("Benchmark:", title) | ||
| async def run_benchmark( |
There was a problem hiding this comment.
In my opinion this should be an instance method of Benchmark named run.
benchmarks/benchmark_runner.py
Outdated
| @@ -116,11 +123,8 @@ async def compare_diffs(actual, generated): | |||
| return await grade(prompt, comparison_prompt) | |||
|
|
|||
|
|
|||
| async def grade_and_clean_diff(repo, response, result, comparison_diff=None): | |||
| async def grade_and_clean_diff(diff, response, result, comparison_diff=None): | |||
There was a problem hiding this comment.
This doesn't clean anymore. I think we should rename to grade_diff. I like the change to having setup clean instead of teardown. It's good to have the benchmark repo easily inspectable after a benchmark.
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.
This makes use of the Sampler as much as possible for benchmarks. Basically there's now a
class Benchmark, which has a list of samples, and it evaluates each withrun_sample.Pull Request Checklist