docs: add warning about deduplication

[kjappelbaum]

Summary by Sourcery

Add a warning in the documentation about the limitations of deduplication in pretraining datasets, advising users on potential data leakage issues.

Documentation:

• Add a warning about the potential issues with deduplication in pretraining datasets, highlighting that datasets are only deduplicated based on the CIF string, which may lead to data leakage if structures with slightly translated positions are present.

[sourcery-ai]

Reviewer's Guide by Sourcery

This pull request adds a warning about deduplication in the benchmarking documentation. It explains that the pretraining datasets in MatText are only deduplicated based on the CIF string, which may lead to data leakage issues in certain use cases. The PR also includes minor formatting and whitespace changes throughout the document.

File-Level Changes

Change	Details	Files
Added a warning about deduplication in pretraining datasets	Explained that pretraining datasets are only deduplicated based on CIF string Warned about potential data leakage issues Suggested using other representations for deduplication if needed	docs/benchmarking.md
Made minor formatting and whitespace adjustments	Removed trailing whitespaces Adjusted line breaks and indentation Fixed typos and improved readability	docs/benchmarking.md

---

Tips

• Trigger a new Sourcery review by commenting @sourcery-ai review on the pull request.
• Continue your discussion with Sourcery by replying directly to review comments.
• You can change your review settings at any time by accessing your dashboard:
  • Enable or disable the Sourcery-generated pull request summary or reviewer's guide;
  • Change the review language;
• You can always contact us if you have any questions or feedback.

[sourcery-ai]

Hey @kjappelbaum - I've reviewed your changes and they look great!

Here's what I looked at during the review

• 🟢 General issues: all looks good
• 🟢 Security: all looks good
• 🟢 Testing: all looks good
• 🟢 Complexity: all looks good
• 🟡 Documentation: 3 issues found

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment to tell me if it was helpful.}

[sourcery-ai]

nitpick (documentation): Remove trailing whitespace

There are several instances of trailing whitespace throughout the document. Consider removing all trailing whitespace for consistency.

[kjappelbaum]

can you make this into a suggestion I can apply?

[sourcery-ai]

Certainly! Here's a suggestion you can apply to remove the trailing whitespace:

Suggested change

	python main.py -cn=benchmark model=benchmark_example +model.dataset_type=filtered +model.representation=composition +model.dataset=perovskites +model.checkpoint=path/to/checkpoint
	python main.py -cn=benchmark model=benchmark_example +model.dataset_type=filtered +model.representation=composition +model.dataset=perovskites +model.checkpoint=path/to/checkpoint
	```
	Here, for the benchmarking pipeline(`-cn=benchmark`) the base config is `benchmark_example.yaml`.
	Here, for the benchmarking pipeline(`-cn=benchmark`) the base config is `benchmark_example.yaml`.
	You can define the parameters for the experiment hence at `\conf\model\benchmark_example.yaml`.
	Here, for the benchmarking pipeline(`-cn=benchmark`) the base config is `benchmark_example.yaml`.

You can apply this suggestion directly to the diff hunk. Let me know if you need further assistance!

[sourcery-ai]

suggestion (documentation): Standardize code block formatting

Some code blocks use triple backticks with a language specifier (e.g., ```bash), while others use just triple backticks. Consider standardizing all code blocks to include the language specifier for consistency and improved syntax highlighting.

[n0w0f]

Looks great to me. Thanks @kjappelbaum