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>
33 lines
1018 B
Python
33 lines
1018 B
Python
"""OpenAI MRCR (multi-round coreference, long-context). Mirror: openai-mirror/mrcr."""
|
|
|
|
from ..sample import Sample
|
|
from ..registry import register_dataset
|
|
from ..spec import DatasetSpec
|
|
|
|
|
|
@register_dataset(
|
|
DatasetSpec(
|
|
name='openai_mrcr',
|
|
source='openai/mrcr', # OFFICIAL OpenAI release (HuggingFace)
|
|
subset='2needle', # or 4needle / 8needle
|
|
split='test',
|
|
task_type='qa',
|
|
tags=['long_context'],
|
|
description='OpenAI MRCR long-context retrieval/coreference (official).',
|
|
params={'hub': 'hf_raw'},
|
|
)
|
|
)
|
|
def openai_mrcr():
|
|
def to_sample(record: dict) -> Sample:
|
|
return Sample(
|
|
input=record['prompt'],
|
|
target=str(record['answer']).strip(),
|
|
metadata={
|
|
'n_needles': record.get('n_needles'),
|
|
'total_messages': record.get('total_messages'),
|
|
'random_string_to_prepend': record.get('random_string_to_prepend'),
|
|
},
|
|
)
|
|
|
|
return to_sample
|