> ## Documentation Index
> Fetch the complete documentation index at: https://fireworks.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Weights & Biases Integration

> Track Fireworks fine-tuning experiments in Weights & Biases with real-time training loss, accuracy, and hyperparameters for managed SFT, DPO, and RFT jobs.

Fireworks AI integrates with [Weights & Biases (W\&B)](https://wandb.ai) to provide observability into your training jobs. All training metrics sync in real-time to your W\&B workspace.

## Prerequisites

* W\&B account at [wandb.ai](https://wandb.ai)
* W\&B API key from [wandb.ai/authorize](https://wandb.ai/authorize)

## Integration Guides

> [card] [Supervised Fine-Tuning](https://fireworks.ai/docs/fine-tuning/fine-tuning-models.md#additional-managed-training-job-settings)
>
> Enable W\&B tracking for supervised fine-tuning jobs

> [card] [Reinforcement Learning](https://fireworks.ai/docs/fine-tuning/training-api/cookbook/reference.md#wandbconfig)
>
> Track Training API RL runs with W\&B

> [card] [DPO Training](https://fireworks.ai/docs/tools-sdks/firectl/commands/dpo-job-create.md#flags)
>
> Enable W\&B for Direct Preference Optimization jobs


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.