Fireworks Training Cookbook

Training loops for RL, preference optimization, SFT and embedding fine-tuning on Fireworks. Full docs: Training API.

New here? The Muse Glimmer mini cookbook runs a free first fine-tune on preloaded example data in about 10 minutes.

Versioned installations

Applications can depend on fireworks-training-cookbook==<version> from PyPI instead of a Git URL once the first release has been published. Imports remain training.*. GitHub tag cookbook-v2026.10.26.1 maps to version 2026.10.26.1 (an illustrative version; select an available version from PyPI).

Layout

The tree is layered so each kind of change has one home:

recipes/              One file per training loop; fork to change the algorithm
recipes/experiment/   Loops not yet stable (serverless async RL, SAO/PPO)
utils/                Reusable pieces recipes assemble: config, data, losses,
                      rollout helpers, metrics (structured, per step)
examples/             Task code + one recipe call; no loop logic
  muse_glimmer/        Free first fine-tune walkthrough (Managed and serverless SFT)
  sft/ dpo/ orpo/ embedding/ distillation/
  rl/                 deepmath (text) · visual_toolbench (vision) ·
                      frozen_lake (multi-turn env) · multihop_qa (IGPO) ·
                      experiment/sao
  harbor_rl/          Sandboxed agentic RL: tasks/ × harnesses/ over tito/
  tools/              Standalone checkpoint, promotion and trainer utilities
  archive/            Deprecated examples, kept importable; do not extend
case-studies/         End-to-end notebooks (data -> eval -> train -> eval)
renderer/             Chat renderers and parity verifier
datasets/             Lightweight dataset validation and image geometry checks
tests/                Unit and smoke tests

Inside an example folder, train_<task>.py runs on a dedicated trainer + deployment and train_<task>_serverless.py on the shared serverless pool with the same task code. A new task belongs in examples/; a new objective in a forked recipe; anything two recipes need in utils/. Dataset checks shared with preflight validation belong in datasets/, which stays independent of the renderer registry and training runtime.

Recipes

Sync RL collects and trains one complete batch; async RL sends currently ready groups together. Both wait for every backward before one optimizer update. prompt_groups_per_step defines optimizer membership; remove the old pipeline_chunks_per_step field. See the skills for losses and metrics.

To train another RL objective, fork a recipe and replace its loss implementation; see rl-custom-loss.md. Optional reference KL uses utils/rl/reference.py: LoRA scores the frozen base with adapters disabled on its trainer; full-parameter tuning scores a separate frozen base-model inference deployment. Reference setup and scoring stay outside both stock loops.

Case studies

Self-contained, runnable notebooks in case-studies/ — each takes one real problem end-to-end (build data -> evaluate the base model -> fine-tune -> evaluate again and measure the improvement). These run on the Fireworks Python SDK (fireworks-ai) plus the eval-protocol framework — no firectl required. Most need no cookbook training loop either; embedding_support_search is the exception, since it drives recipes/embedding_loop.py directly.

Case study	Technique	Dataset	"Customer problem"	Open
sft_prompt_router	Text SFT / classification (Python SDK), dedicated + serverless	Prompt-Routing-Dataset	Route prompts to a small vs big model (multi-field classifier)	dedicated · serverless
sft_cord_receipts	Vision SFT (Python SDK)	CORD receipts	Teach the model a new structured-output task
dpo_style	DPO (Python SDK)	HelpSteer3	"Write the way we write" (style/quality preferences)
reasoning_rl	GRPO via Training API (legacy managed RFT notebook is deprecated)	GSM8K	Improve step-by-step reasoning	deepmath
embedding_support_search	Contrastive embedding fine-tuning (embedding_loop recipe)	Airbnb Help Center scenarios	Retrieve the help article that governs a situation, not the one that sounds like it
agentic_rl_text2sql	Serverless tool-calling GRPO (Training API SDK)	BIRD text-to-SQL	Train a multi-turn tool-calling SQL agent; evaluate on unseen (out-of-distribution) databases
sft_bfcl_toolcalls	SFT on the Training API: serverless, dedicated, and managed compared (Python SDK)	xLAM function-calling-60k + xlam-irrelevance-7.5k, scored on BFCL V4 non-live	Fix tool-call emission/abstention on a public benchmark, not a metric we invented
multilora_fleet	LoRA SFT + multi-LoRA serving (Python SDK)	MASSIVE (51 locales)	One deployment, a per-tenant specialist for every locale
grpo_countdown	Serverless non-agentic GRPO (Training API SDK)	TinyZero Countdown	Own the single-turn GRPO loop on serverless; same algorithm as a dedicated config swap

Setup. Follow the install instructions below, using uv pip install -e '.[eval]' to include the SDK and Eval Protocol, and create a .env with FIREWORKS_API_KEY (FIREWORKS_ACCOUNT_ID for the deploy/RFT cells). A couple of case studies add extras, noted in their own READMEs. Train/deploy cells provision real GPU and cost money. Each folder has its own README with the specifics.

Open Weight Room

Open Weight Room case studies explore changes in model behavior through small adapters: concise answers, editing, output constraints, writing style, visual design, and clarification before acting. Each study includes recorded evidence and explains its evaluation limits. Training walkthroughs and recorded-results analyses are labeled separately.

Getting started

Use Python 3.11 or newer. For released training.* recipes and utilities:

python -m pip install --upgrade fireworks-training-cookbook

For the runnable notebooks and examples below, clone the source and install it in editable mode:

git clone https://github.com/fw-ai-external/cookbook.git && cd cookbook/training
uv venv --python 3.12 && source .venv/bin/activate
uv pip install -e .                      # installs the SDK and recipe dependencies
export FIREWORKS_API_KEY=...             # or put it in training/.env
python -m training.examples.sft.train_sft --help

The eval and dev extras install eval-protocol==0.3.33 from PyPI, which supports the tested LiteLLM 1.105.0 release.

Each recipe's Config dataclass documents its fields. Leave TrainerConfig() empty for SDK-selected defaults, or set training_shape_id; deployments resolve their shape from the training shape. Weight sync, shapes, HSDP replicas, reservations and distillation teachers are covered by the skills and the configuration reference.

Tests

uv pip install -e ".[dev]"
pytest tests/

SDFT

SDFT is maintained in the Fireworks Tinker-Cookbook fork. See the customer guide for where to start.

Publishing releases

Releases are managed by the maintainers' private CI after the reviewed promotion PR merges. Promotion commits the calendar version in pyproject.toml and the root package entry in uv.lock before review. For example, cookbook-v2026.1.2.1 publishes package version 2026.1.2.1.

The publisher builds the wheel from the source distribution, validates both artifacts, publishes to PyPI, and verifies the installed version. This repository has no publishing workflow or stored release credentials. Contact a maintainer to retry a failed release.

The eval extra pins eval-protocol==0.3.33. Release builds reject direct URL dependencies in all extras so Git pins cannot break PyPI publication.