[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot] 2025-11-13 08:04:36 +00:00
parent 3f6265563f
commit b03b8d3808

View file

@ -309,7 +309,6 @@ class GSM8kEnv(BaseEnv):
masks = item["masks"]
logprobs = item["logprobs"]
# remove obviously bad examples
if len([1 for i in masks if i != -100]) < 10:
continue
@ -317,7 +316,7 @@ class GSM8kEnv(BaseEnv):
scores["masks"].append(masks)
scores["inference_logprobs"].append(logprobs)
scores["scores"].append(1.0 if reward else -1.0)
if len(scores["tokens"]) >= self.config.group_size:
break