metadata

license: apache-2.0
language:
  - code
  - en
tags:
  - code
  - commit_message_generation
datasets:
  - JetBrains-Research/commit-chronicle
pipeline_tag: text2text-generation

CMG/CMC: CodeReviewer (without history)

This is the checkpoint for CodeReviewer model, fine-tuned for the commit message generation (and/or completion) task as part of the paper "From Commit Message Generation to History-Aware Commit Message Completion", ASE 2023.

Details

🔍 For further details, please refer to:

Paper: https://arxiv.org/abs/2308.07655

Repository: https://github.com/JetBrains-Research/commit_message_generation

This model is based on microsoft/codereviewer checkpoint from 📜 Automating Code Review Activities by Large-Scale Pre-training.
This model was trained with commit diffs, WITHOUT commit message history.
This model was trained on the CommitChronicle dataset introduced in our study.

Our hyperparameter setting is mostly based on 📜 RACE: Retrieval-augmented Commit Message Generation. The exact values are provided below:

Hyperparameter	Value
Encoder context max length	512
Decoder context max length	512
Number of training epochs	1
Batch size	32
Optimizer	AdamW
Warmup	Linear
Number of warmup steps	100
Peak learning rate	0.00002

Available checkpoints

We also released checkpoints for other models fine-tuned as part of our study.

Models trained with commit message history:
- CodeT5: 🤗 JetBrains-Research/cmg-codet5-with-history
- CodeReviewer: 🤗 JetBrains-Research/cmg-codereviewer-with-history
- RACE: 🤗 JetBrains-Research/cmg-race-with-history
Models trained without commit message history:
- CodeT5: 🤗 JetBrains-Research/cmg-codet5-without-history
- CodeReviewer: 🤗 JetBrains-Research/cmg-codereviewer-without-history (this model)
- RACE: 🤗 JetBrains-Research/cmg-race-without-history

Citation

TODO