Skip to content

Added comprehensive training.md guide for model training setup#126

Closed
Sharkyii wants to merge 2 commits intoopenclimatefix:mainfrom
Sharkyii:training-readme
Closed

Added comprehensive training.md guide for model training setup#126
Sharkyii wants to merge 2 commits intoopenclimatefix:mainfrom
Sharkyii:training-readme

Conversation

@Sharkyii
Copy link
Copy Markdown

Description

This PR adds a comprehensive training.md guide to make PVNet model training more accessible and user-friendly for open-source contributors.

The new documentation provides:

  • Step-by-step configuration guide for all required YAML files with exact file paths and line numbers
  • Clear data download instructions using AWS CLI for GFS and GSP datasets
  • Sample generation workflow with local data optimization to avoid slow S3 streaming
  • Training execution guide with proper datamodule switching between sample generation and training
  • Configuration summary tables showing workflow states and key file purposes
  • Troubleshooting section covering common setup issues (slow generation, path errors, memory issues, W&B authentication)

Impact:

This documentation reduces the barrier to entry for new contributors by providing a complete, tested workflow for running PVNet training. It addresses setup friction points that are common pain points for volunteers joining the project.

Fixes #7

How Has This Been Tested?

  • Yes

Verification performed:

  1. All file paths verified against actual project structure
  2. YAML configuration snippets checked against source files (including line numbers)
  3. AWS S3 bucket paths confirmed to match project data sources
  4. Command syntax tested for accuracy

If your changes affect data processing, have you plotted any changes? i.e. have you done a quick sanity check?

  • N/A (documentation-only change)

Checklist:

  • My code follows OCF's coding style guidelines
  • I have performed a self-review of my own code
  • I have made corresponding changes to the documentation
  • N/A - I have added tests that prove my fix is effective or that my feature works
  • I have checked my code and corrected any misspellings

@Sharkyii
Copy link
Copy Markdown
Author

Sharkyii commented Feb 2, 2026

@siddharth7113 could you please review it

@siddharth7113
Copy link
Copy Markdown
Contributor

Apologies, I didn't get time to see it but I think there is another PR merged for this already

@Sharkyii
Copy link
Copy Markdown
Author

@siddharth7113 could you please pin point it?
I thinks there is none for documentation of training setup
For #7

@Sharkyii Sharkyii closed this Feb 16, 2026
@Sharkyii Sharkyii deleted the training-readme branch March 31, 2026 04:23
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

train model + evaluate model

2 participants