nemo_rl.data.processors

Contains data processors for evaluation.

Module Contents

Functions

helpsteer3_data_processor	Process a HelpSteer3 preference datum into a DatumSpec for GRPO training.
math_data_processor	Process a datum dictionary (directly loaded from dataset) into a DatumSpec for the Math Environment.
math_hf_data_processor	Process a datum dictionary (directly loaded from data/hf_datasets/openmathinstruct2.py) into a DatumSpec for the Reward Model Environment.
_construct_multichoice_prompt	Construct prompt from question and options.
multichoice_qa_processor	Process a datum dictionary (directly loaded from dataset) into a DatumSpec for multiple-choice problems.
register_processor

Data

TokenizerType
PROCESSOR_REGISTRY

API

nemo_rl.data.processors.TokenizerType

None

nemo_rl.data.processors.helpsteer3_data_processor(

datum_dict: dict[str, Any],

task_data_spec: nemo_rl.data.interfaces.TaskDataSpec,

tokenizer: nemo_rl.data.processors.TokenizerType,

max_seq_length: int,

idx: int,

) → nemo_rl.data.interfaces.DatumSpec

Process a HelpSteer3 preference datum into a DatumSpec for GRPO training.

This function converts HelpSteer3 preference data to work with GRPO by:

1. Using the context as the prompt

2. Using the preferred completion as the target response

3. Creating a reward signal based on preference scores

nemo_rl.data.processors.math_data_processor(

datum_dict: dict[str, Any],

task_data_spec: nemo_rl.data.interfaces.TaskDataSpec,

tokenizer: nemo_rl.data.processors.TokenizerType,

max_seq_length: int,

idx: int,

) → nemo_rl.data.interfaces.DatumSpec

Process a datum dictionary (directly loaded from dataset) into a DatumSpec for the Math Environment.

nemo_rl.data.processors.math_hf_data_processor(

datum_dict: dict[str, Any],

task_data_spec: nemo_rl.data.interfaces.TaskDataSpec,

tokenizer: nemo_rl.data.processors.TokenizerType,

max_seq_length: int,

idx: int,

) → nemo_rl.data.interfaces.DatumSpec

Process a datum dictionary (directly loaded from data/hf_datasets/openmathinstruct2.py) into a DatumSpec for the Reward Model Environment.

nemo_rl.data.processors._construct_multichoice_prompt(

prompt: str,

question: str,

options: dict[str, str],

) → str

Construct prompt from question and options.

nemo_rl.data.processors.multichoice_qa_processor(

datum_dict: dict[str, Any],

task_data_spec: nemo_rl.data.interfaces.TaskDataSpec,

tokenizer: nemo_rl.data.processors.TokenizerType,

max_seq_length: int,

idx: int,

) → nemo_rl.data.interfaces.DatumSpec

Process a datum dictionary (directly loaded from dataset) into a DatumSpec for multiple-choice problems.

nemo_rl.data.processors.PROCESSOR_REGISTRY: Dict[str, nemo_rl.data.interfaces.TaskDataProcessFnCallable]

‘cast(…)’

nemo_rl.data.processors.register_processor(

processor_name: str,

processor_function: nemo_rl.data.interfaces.TaskDataProcessFnCallable,

) → None