Add a fingerprint for each EvaluationModule

[mathemakitten]

In order to support #126 we need to fingerprint whichever EvaluationModule (metric, measurement, etc) we're using for later reproducibility.

This extracts the already-computed hash from each EvaluationModule and makes it easy to access in the evaluation_cls via module._fingerprint, similar to how in datasets you can do ds._fingerprint.

Test via

module = evaluate.load("lvwerra/element_count", module_type="measurement")
print(f"Module fingerprint: {module._fingerprint}")

[HuggingFaceDocBuilderDev]

The documentation is not available anymore as the PR was closed or merged.

[lvwerra]

LGTM! Also interested to hear what @lhoestq thinks. We plan to use this to cache evaluator computations.

Please wait with merging - want to do a minor release first.

[lhoestq]

In datasets we use fingerprint to identify data, while we use hash to identify dataset scripts. For example a DatasetBuilder has a hash that identifies the code of the dataset script it is going to run.

Not a strong opinion but I think you can also name it hash for consistency

[lvwerra]

Sounds good to me - also have no strong opinion :)

[mathemakitten]

Renamed, thanks for the clarification on hash vs. fingerprint!