# LoRA Speedrun: A Leaderboard for Fine-Tuning Techniques

A leaderboard measuring and comparing the speed of techniques.

- **Source:** [Hacker News](https://news.ycombinator.com)
- **Published:** 2026-07-20
- **Topic:** [Data & AI](https://brifing.si/c/data-ai)
- **Original article:** <https://github.com/Saivineeth147/lora-speedrun>
- **On Brifing:** https://brifing.si/s/59b6ebe0-8615-4e4c-bff5-a4e21d21af2c

## What is LoRA Speedrun?

LoRA Speedrun is a leaderboard that measures the fine-tuning times of models like Qwen2.5-1.5B on tasks like GSM8K. Techniques are compared fairly by keeping hardware and tasks constant.

## How Does It Work?

Participants test their techniques on a Modal L40S sandbox for a specific task. Each record is independently run three times on the same hardware and verified. This process is free and open to everyone.

## Current Records

The current record for the GSM8K task is 6 minutes 5 seconds by @Saivineeth147. This technique uses sequence packing and loss masking to achieve higher accuracy and faster results.

## Second Track: SQuAD v1.1

The second track targets the SQuAD v1.1 task with the SmolLM2-1.7B model. This track does not yet have a record and is waiting for its first entry. Both tracks include different model families and task types.

## Why It Matters

LoRA/QLoRA is widely used for fine-tuning in the real world. However, techniques are tested on different models, data, and hardware, making comparisons difficult. This leaderboard provides a fair competitive environment.

## Future and Contribution

LoRA Speedrun can be expanded with more techniques and tracks. Participants can develop new techniques to secure a place on the leaderboard and contribute to the advancement of AI fine-tuning techniques.

## Sources covering this story

- https://github.com/Saivineeth147/lora-speedrun — 

---

_Summary written by Brifing from the original reporting. Copyright in the original article belongs to its publisher; read the full piece at the link above._