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

more linter nonsense

Browse source
This commit is contained in:
teknium 2025-12-24 11:04:33 +00:00
parent f18d46549d
commit abdda3978a
29 changed files with 113 additions and 151 deletions
Download patch file Download diff file Expand all files Collapse all files

4
environments/eval_environments/mixeval_eval.py
View file

@ -343,7 +343,7 @@ class MixEvalEnv(BaseEnv):
if not self._dataset_loaded:
await self._load_dataset()
print(f"\nMixEval Evaluation Setup (with LLM Judge):")
print("\nMixEval Evaluation Setup (with LLM Judge):")
print(f" Dataset: {self.config.dataset_name}")
print(f" Difficulty: {self.config.difficulty}")
print(f" Question types: {self.config.question_types}")
@ -737,7 +737,7 @@ class MixEvalEnv(BaseEnv):
print(f" Format Compliance: {format_valid / total:.2%}")
print(f" Thinking Utilization: {has_thinking / total:.2%}")
print(f" Judge Error Rate: {self.judge_error_count / total:.2%}")
print(f"\n Per-Benchmark Breakdown:")
print("\n Per-Benchmark Breakdown:")
for bench, data in sorted(
benchmark_metrics.items(), key=lambda x: -x[1]["avg_score"]
):