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
1.0 KiB
Python
32 lines
1.0 KiB
Python
"""HellaSwag (official source: rowanz/hellaswag)."""
|
|
|
|
from ..sample import Sample
|
|
from ..registry import register_dataset
|
|
from ..spec import DatasetSpec
|
|
|
|
_LETTERS = 'ABCD'
|
|
|
|
|
|
@register_dataset(
|
|
DatasetSpec(
|
|
name='hellaswag',
|
|
source='Rowan/hellaswag', # parquet conversion of the official rowanz/hellaswag
|
|
split='validation',
|
|
task_type='mcq',
|
|
tags=['commonsense'],
|
|
description='HellaSwag commonsense sentence completion (official).',
|
|
)
|
|
)
|
|
def hellaswag():
|
|
def to_sample(record: dict) -> Sample:
|
|
return Sample(
|
|
# es adapter parity: ctx_a + ' ' + ctx_b.capitalize() -- the
|
|
# mirror's pre-joined `ctx` keeps ctx_b lowercase, es capitalizes
|
|
input=str(record['ctx_a']).strip() + ' ' + str(record['ctx_b']).strip().capitalize(),
|
|
choices=list(record['endings']),
|
|
target=_LETTERS[int(record['label'])],
|
|
metadata={'activity_label': record.get('activity_label')},
|
|
)
|
|
|
|
return to_sample
|