docs: add DPA3 cyclohexane distillation tutorial - #5564
Conversation
|
Important Review skippedReview was skipped as selected files did not have any reviewable changes. 💤 Files selected but had no reviewable changes (1)
⚙️ Run configurationConfiguration used: Repository UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
You can disable this status message by setting the Use the checkbox below for a quick retry:
📝 WalkthroughWalkthroughAdds a comprehensive knowledge distillation tutorial notebook ( ChangesKnowledge distillation tutorial notebook and documentation navigation
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
66dca05 to
64dcc59
Compare
Authored by OpenClaw (model: custom-chat-jinzhezeng-group/gpt-5.5)
64dcc59 to
053483f
Compare
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## master #5564 +/- ##
==========================================
- Coverage 82.17% 82.14% -0.03%
==========================================
Files 898 900 +2
Lines 103576 104138 +562
Branches 4432 4473 +41
==========================================
+ Hits 85117 85548 +431
- Misses 17063 17181 +118
- Partials 1396 1409 +13 ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
iProzd
left a comment
There was a problem hiding this comment.
A few issues should be fixed before merging:
-
The text repeatedly says the workflow extracts/trains on
energy,force, andviriallabels, but the generated dataset contains onlyenergy/forceand the training config sets the virial loss weights to 0. Please update the wording to avoid implying that virials are used in this case. -
Some saved notebook outputs show “3Dmol.js failed to load” with large inline JavaScript blocks. These should be cleared or replaced with static outputs before adding the notebook to the official docs.
-
The text says the Teacher MD uses 5,000 steps, but the code sets
MD_STEPS = 500. Please make these consistent.
|
I'll let the agent fix 1 and 3. Regarding 2,
3Dmol is rendered correctly on the web page. https://deepmodeling--5564.org.readthedocs.build/projects/deepmd/en/5564/getting-started/dpa3_cyclohexane_distillation.html |
Clarify that the lightweight distillation dataset uses energy and force labels only, while virial loss remains disabled, and make the Teacher MD step count match the documented 5,000 steps. Authored by OpenClaw (model: custom-chat-jinzhezeng-group/gpt-5.5)
Align the Teacher MD prose with the existing 500-step code path so the tutorial remains quick to run. Authored by OpenClaw (model: custom-chat-jinzhezeng-group/gpt-5.5)
Clear executed notebook outputs and execution counts, remove runtime-specific metadata, and normalize the kernelspec before rendering in docs. Authored by OpenClaw (model: custom-chat-jinzhezeng-group/gpt-5.5)
Restore rendered tutorial outputs while clearing the package-install output and removing notebook runtime protocol metadata. Authored by OpenClaw (model: custom-chat-jinzhezeng-group/gpt-5.5)
Summary
Checks
ast.parsegit diff --checkAuthored by OpenClaw (model: custom-chat-jinzhezeng-group/gpt-5.5)
Summary by CodeRabbit