370953729b
- perf_stats aggregator lives in eval/, not model/: the import failed silently and EVERY perf column was empty (not just ttft). Now warns on stderr instead of swallowing. - repeats > 1 get their own checkpoint key (:rep2, :rep3, ...): repeat 2 previously restored repeat 1's predictions and finished instantly with identical scores. rep1 keeps the legacy key (existing checkpoints still resume). - repeats summary: report the MEAN score and aggregate time/tokens over ALL runs (was: last run only). - README: six-benchmark command as the primary example. Co-Authored-By: Claude <noreply@anthropic.com>
30 lines
940 B
Python
30 lines
940 B
Python
"""AI2 ARC (official source: allenai/ai2_arc, ARC-Easy / ARC-Challenge)."""
|
|
|
|
from ..sample import Sample
|
|
from ..registry import register_dataset
|
|
from ..spec import DatasetSpec
|
|
|
|
|
|
@register_dataset(
|
|
DatasetSpec(
|
|
name='arc',
|
|
source='allenai/ai2_arc', # official: https://huggingface.co/datasets/allenai/ai2_arc
|
|
subset='ARC-Easy', # or ARC-Challenge
|
|
split='test',
|
|
task_type='mcq',
|
|
tags=['knowledge', 'science'],
|
|
description='AI2 Reasoning Challenge (official).',
|
|
)
|
|
)
|
|
def arc():
|
|
def to_sample(record: dict) -> Sample:
|
|
choices = record['choices'] # {'text': [...], 'label': [...]}
|
|
return Sample(
|
|
input=record['question'],
|
|
choices=list(choices['text']),
|
|
target=str(record['answerKey']).strip(), # letter label
|
|
metadata={'id': record.get('id'), 'labels': list(choices['label'])},
|
|
)
|
|
|
|
return to_sample
|