Recipes - Adaptive ML Documentation

Recipes are pre-built workflows for training and evaluating models. Run them on Adaptive’s compute infrastructure.

SDK
UI

Run a recipe

job = adaptive.jobs.run(
    recipe_key="sft",
    num_gpus=1,
    args={
        "model_to_train": "llama-3.1-8b-instruct",
        "output_model_key": "my-model-v1",
        "dataset": "my-training-data",
        "epochs": 3,
    },
)

Parameter	Type	Required	Description
`recipe_key`	str	Yes	Recipe identifier (see below)
`num_gpus`	int	Yes	Number of GPUs to use
`args`	dict	Yes	Recipe-specific arguments

Built-in recipes

Training:

Recipe	Key	Use when
Supervised fine-tuning	`sft`	You have high-quality completions
RL on preferences	`preference_rlhf`	You have preferred/rejected pairs
RL on metrics	`metric_rlhf`	You have completion-level scores
RL with grader	`rl`	Criteria can be expressed in natural language

Evaluation:

Recipe	Key	Use when
Evaluate with grader	`eval`	Comparing model performance

Run an evaluation

adaptive.jobs.run(
    recipe_key="eval",
    num_gpus=2,
    args={
        "dataset": "eval-prompts",
        "models_to_evaluate": ["model-a", "model-b"],
        "graders": ["quality-judge"],
    },
)

Results appear as evaluation artifacts with score tables and per-sample interactions. Evaluations use Graders to score completions.For custom recipes, see Custom Recipes.See SDK Reference for all job methods.