# Overview

Fine-tune LLMs on your Lightning Rod datasets. The training API supports LoRA fine-tuning with configurable base models, training steps, batch size, and rank.

> **Early Access** — The training API is in preview and not fully stable. [Join the early access waitlist](https://www.lightningrod.ai/training-waitlist) to get access and stay updated.

## Workflow

1. **Generate Dataset** — Use the dataset generation pipeline to create labeled forecasting samples
2. **Prepare Data** — Run `filter_and_split()` to filter, deduplicate, and split into train/test datasets
3. **Configure Training** — Set base model, training steps, and optional LoRA parameters
4. **Train** — Submit a training job and monitor progress
5. **Evaluation** — Run evals against your test dataset
6. **Inference** — Use the trained model via `lr.predict()` or the OpenAI-compatible API

## Key Capabilities

* LoRA fine-tuning with configurable rank and batch size
* Configurable base models (e.g. Qwen, Llama)
* Cost estimation before running
* Live progress monitoring in notebooks
* OpenAI-compatible inference with your trained model
* Built-in evals against test datasets

## Next Steps

* [Data Preparation](/python-sdk/fine-tuning-beta/data-preparation.md) — Use `filter_and_split()` to get training-ready datasets
* [Training](/python-sdk/fine-tuning-beta/training.md) — Configure and run training jobs
* [Evaluation](/python-sdk/fine-tuning-beta/evaluation.md) — Evaluate your trained model
* [Inference](/python-sdk/fine-tuning-beta/inference.md) — Use your trained model for predictions


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.lightningrod.ai/python-sdk/fine-tuning-beta/overview.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.