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>
32 lines
1023 B
Python
32 lines
1023 B
Python
"""AIME 2024 (community-standard mirror: HuggingFaceH4/aime_2024).
|
|
|
|
AIME has no official HF release; this is the widely used mirror.
|
|
"""
|
|
|
|
from ..sample import Sample
|
|
from ..registry import register_dataset
|
|
from ..spec import DatasetSpec
|
|
|
|
|
|
@register_dataset(
|
|
DatasetSpec(
|
|
name='aime24',
|
|
source='HuggingFaceH4/aime_2024', # https://huggingface.co/datasets/HuggingFaceH4/aime_2024
|
|
split='train', # the dataset ships a single split
|
|
gen_config={'temperature': 1.0, 'max_tokens': 8192},
|
|
prompt_style='aime_es', # es MathArena template: instruction-first,
|
|
task_type='math',
|
|
tags=['math', 'competition'],
|
|
description='AIME 2024, 30 problems (integer answers 000-999).',
|
|
)
|
|
)
|
|
def aime24():
|
|
def to_sample(record: dict) -> Sample:
|
|
return Sample(
|
|
input=record['problem'],
|
|
target=str(record['answer']).strip(),
|
|
metadata={'id': record.get('id'), 'solution': record.get('solution')},
|
|
)
|
|
|
|
return to_sample
|