Skip to content
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

fix(pt): finetuning property/dipole/polar/dos fitting with multi-dimensional data causes error #4145

Merged
merged 16 commits into from
Sep 25, 2024

Conversation

Chengqian-Zhang
Copy link
Collaborator

@Chengqian-Zhang Chengqian-Zhang commented Sep 19, 2024

Fix issue #4108

If a pretrained model is labeled with energy and the out_bias is one dimension. If we want to finetune a dos/polar/dipole/property model using this pretrained model, the out_bias of finetuning model is multi-dimension(example: numb_dos = 250). An error occurs:
RuntimeError: Error(s) in loading state_dict for ModelWrapper:
size mismatch for model.Default.atomic_model.out_bias: copying a param with shape torch.Size([1, 118, 1]) from checkpoint, the shape in current model is torch.Size([1, 118, 250]).
size mismatch for model.Default.atomic_model.out_std: copying a param with shape torch.Size([1, 118, 1]) from checkpoint, the shape in current model is torch.Size([1, 118, 250]).

When using new fitting, old out_bias is useless because we will recompute the new bias in later code. So we do not need to load old out_bias when using new fitting finetune.

Summary by CodeRabbit

  • New Features

    • Enhanced parameter collection for fine-tuning, refining criteria for parameter retention.
    • Introduced a model checkpoint file for saving and resuming training states, facilitating iterative development.
  • Tests

    • Added a new test class to validate training and fine-tuning processes, ensuring model performance consistency across configurations.

Copy link
Contributor

coderabbitai bot commented Sep 19, 2024

Walkthrough

Walkthrough

The pull request modifies the logic in the collect_single_finetune_params function within training.py, refining the criteria for parameter selection during fine-tuning. A new model checkpoint file is added to support model persistence, and a new test class is introduced to validate both training and fine-tuning processes, enhancing the testing framework.

Changes

Files Change Summary
deepmd/pt/train/training.py Updated collect_single_finetune_params to exclude parameters containing ".descriptor." when _new_fitting is true.
source/checkpoint Added a new model checkpoint file model.ckpt-1.pt for saving model state during training.
source/tests/pt/test_training.py Introduced TestPropFintuFromEnerModel class with tests for training and fine-tuning processes, including setup and teardown methods.

Possibly related PRs

Suggested reviewers

  • njzjz
  • iProzd
  • wanghan-iapcm

Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL

Commits

Files that changed from the base of the PR and between cf8bac4 and e51a4f7.

Files selected for processing (1)
  • deepmd/pt/train/training.py (1 hunks)
Files skipped from review as they are similar to previous changes (1)
  • deepmd/pt/train/training.py

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

Share
Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    -- I pushed a fix in commit <commit_id>, please review it.
    -- Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    -- @coderabbitai generate unit testing code for this file.
    -- @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    -- @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    -- @coderabbitai read src/utils.ts and generate unit testing code.
    -- @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    -- @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 2

Review details

Configuration used: CodeRabbit UI
Review profile: CHILL

Commits

Files that changed from the base of the PR and between ba9f02f and 1dac68c.

Files selected for processing (1)
  • deepmd/pt/train/training.py (1 hunks)

deepmd/pt/train/training.py Outdated Show resolved Hide resolved
deepmd/pt/train/training.py Outdated Show resolved Hide resolved
@Chengqian-Zhang Chengqian-Zhang marked this pull request as draft September 19, 2024 05:39
Copy link

codecov bot commented Sep 19, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 83.43%. Comparing base (f5cfeab) to head (e51a4f7).
Report is 3 commits behind head on devel.

Additional details and impacted files
@@            Coverage Diff             @@
##            devel    #4145      +/-   ##
==========================================
+ Coverage   83.42%   83.43%   +0.01%     
==========================================
  Files         532      532              
  Lines       52048    52049       +1     
  Branches     3046     3046              
==========================================
+ Hits        43419    43429      +10     
+ Misses       7682     7672      -10     
- Partials      947      948       +1     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@Chengqian-Zhang Chengqian-Zhang marked this pull request as ready for review September 19, 2024 11:50
deepmd/pt/train/training.py Outdated Show resolved Hide resolved
@njzjz njzjz added this pull request to the merge queue Sep 25, 2024
github-merge-queue bot pushed a commit that referenced this pull request Sep 25, 2024
Fix failed uts in #4145 .

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

- **New Features**
- Added a `"seed"` property to multiple JSON configuration files,
enhancing control over randomness in model training and evaluation.
- Introduced a global seed parameter in various test functions to
improve reproducibility across test runs.

- **Bug Fixes**
- Ensured consistent random number generation in tests by integrating a
global seed parameter.

- **Documentation**
- Updated configuration files and test methods to reflect the addition
of the seed parameter for clarity and consistency.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Merged via the queue into deepmodeling:devel with commit 0b3f860 Sep 25, 2024
61 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[BUG] finetuning property fitting with multi-dimensional data causes error
4 participants