Function _squad_metric

test/general/lm_eval/tasks/squad.py:35–37 · view source on GitHub ↗

(predictions, references)

Source from the content-addressed store, hash-verified

33
34
35	def _squad_metric(predictions, references):
36	squad_metric = datasets.load_metric("squad_v2")
37	return squad_metric.compute(predictions=predictions, references=references)
38
39
40	def _squad_agg(key, items):

_squad_aggFunction · 0.85

no outgoing calls

no test coverage detected