fix(envs): Add source dataset and index to metadata (#388)

* add source dataset and index to metadata

* fix typo

* fix coach class and its test
This commit is contained in:
Zafir Stojanovski 2025-03-20 12:12:14 +01:00 committed by GitHub
parent 7475a20700
commit ce0a6c4878
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
104 changed files with 549 additions and 146 deletions

View file

@ -5,6 +5,8 @@ from typing import Any, Literal, Optional
from ..coaching import BaseCurriculum, RangeAttributeDefinition
from ..factory import ProceduralDataset, register_dataset
DATASET_NAME = "basic_arithmetic"
@dataclass
class BasicArithmeticDatasetConfig:
@ -95,6 +97,8 @@ class BasicArithmeticDataset(ProceduralDataset):
"question": question,
"answer": str(result),
"metadata": {
"source_dataset": DATASET_NAME,
"source_index": idx,
"expression": expression,
"num_terms": num_terms,
"num_digits": num_digits,
@ -260,4 +264,4 @@ class BasicArithmeticCurriculum(BaseCurriculum):
# Register the dataset
register_dataset("basic_arithmetic", BasicArithmeticDataset, BasicArithmeticDatasetConfig, BasicArithmeticCurriculum)
register_dataset(DATASET_NAME, BasicArithmeticDataset, BasicArithmeticDatasetConfig, BasicArithmeticCurriculum)