metadata

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

CMG/CMC: RACE (with history)

This is the checkpoint for RACE 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: TODO

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

This model is based on the fine-tuned CodeT5 checkpoint JetBrains-Research/cmg-codet5-with-history and uses RACE architecture introduced in 📜 RACE: Retrieval-Augmented Commit Message Generation.
- Note: Requires a custom model class. Check our implementation or the replication package provided by RACE authors.
This model was trained with commit diffs as well as WITH 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 (this model)
Models trained without commit message history:
- CodeT5: 🤗 JetBrains-Research/cmg-codet5-without-history
- CodeReviewer: 🤗 JetBrains-Research/cmg-codereviewer-without-history
- RACE: 🤗 JetBrains-Research/cmg-race-without-history

Citation

TODO