# Gradients: When Markets Meet Fine-tuning -- A Distributed Approach to Model Optimisation

arXiv: https://arxiv.org/abs/2506.07940 · HTML: https://mlsanity.com/paper/2506.07940/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 29 of 29)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [BOHB: Robust and Efficient Hyperparameter Optimization at Scale](https://mlsanity.com/paper/1807.01774/) (2018)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.10512/) (2023)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://mlsanity.com/paper/2401.15391/) (2024)
- [When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method](https://mlsanity.com/paper/2402.17193/) (2024)
- [Auto-Keras: An Efficient Neural Architecture Search System](https://mlsanity.com/paper/1806.10282/) (2018)
- [RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2407.11005/) (2024)
- [Biscotti: A Ledger for Private and Secure Peer-to-Peer Machine Learning](https://mlsanity.com/paper/1811.09904/) (2018)
- [BitTensor: A Peer-to-Peer Intelligence Market](https://mlsanity.com/paper/2003.03917/) (2020)
- [Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs](https://mlsanity.com/paper/2409.19759/) (2024)
- [Exploring the Use of Abusive Generative AI Models on Civitai](https://mlsanity.com/paper/2407.12876/) (2024)
- [Incentive Mechanism Design for Distributed Coded Machine Learning](https://mlsanity.com/paper/2012.08715/) (2020)
- [Multi-Objective Population Based Training](https://mlsanity.com/paper/2306.01436/) (2023)
- [AutoTrain: No-code training for state-of-the-art models](https://mlsanity.com/paper/2410.15735/) (2024)

## Abstract (arXiv)

Current AutoML platforms leave substantial performance untapped. Testing 180 fine-tuning tasks across models from 70M to 70B parameters, we found that HuggingFace AutoTrain, TogetherAI, Databricks, and Google Cloud consistently produce suboptimal configurations. Gradients, built on the Bittensor network, attacks this problem through competition. Independent miners race to find optimal hyperparameters, earning rewards proportional to their models' performance. This tournament drives exploration of configuration spaces that single-strategy methods never examine. In our experiments, Gradients achieved a 100% win rate against TogetherAI, Databricks, and Google Cloud, and beat HuggingFace AutoTrain in 82.8% of experiments. Mean improvements reached 42.1% against commercial platforms. Retrieval-augmented generation tasks saw 30-40% gains; diffusion models improved 23.4% on person-specific generation. When miners compete for rewards, they develop optimization strategies that centralized approaches overlook. These findings demonstrate that decentralized systems with economic incentives can systematically outperform traditional AutoML, suggesting market dynamics may be key to achieving superior fine-tuning results. Code is available at https://github.com/rayonlabs/G.O.D.