NousResearch/atropos
1
0
Fork 0
mirror of https://github.com/NousResearch/atropos.git synced 2026-04-19 12:57:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

revert gsm8k

Browse source
This commit is contained in:
Jai Suphavadeeprasit 2026-03-23 11:18:14 -07:00
parent 45f569f3af
commit 79ff1642f8
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
environments/gsm8k_server.py
View file

@ -232,6 +232,7 @@ class GSM8kEnv(BaseEnv):
)
async with self.server.managed_server(tokenizer=self.tokenizer) as managed:
chat_completions = await managed.chat_completion(
messages=[{"role": "system", "content": system_prompt}, user_message],
n=self.config.group_size,
@ -351,7 +352,7 @@ class GSM8kEnv(BaseEnv):
# Apply linear penalty scaling from 1.0 down to 0.0
scores["scores"].append(1.0 - percentage_of_range)
if all([scores["scores"][0] == score for score in scores["scores"]]):
return None
return None # If all the same, we return None
return scores
else:
# If the gold solution is not parseable, we return None