epfml/llm-optimizer-benchmark

Benchmarking Optimizers for LLM Pretraining

38
/ 100
Emerging

This project offers a standardized way to compare different optimization techniques used in training Large Language Models (LLMs). It takes various optimizer configurations, model sizes, and training durations as input and produces benchmark results showing which optimizer performs best under specific conditions. LLM researchers and practitioners would use this to inform their choice of optimization methods for pretraining LLMs.

Use this if you are pretraining Large Language Models and need to systematically evaluate and select the most effective optimization technique for your specific model size, batch size, or training duration.

Not ideal if you are looking for a tool to train LLMs for immediate application or if your primary focus is fine-tuning an existing LLM for a downstream task.

LLM pretraining Deep Learning optimization Model development AI research Language model engineering
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 9 / 25

How are scores calculated?

Stars

56

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Dec 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/epfml/llm-optimizer-benchmark"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.