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

6
environments/eval_environments/math_eval.py
View file

@ -178,7 +178,7 @@ class MATHEvalEnv(BaseEnv):
if not self._dataset_loaded:
await self._load_dataset()
print(f"\nMATH Evaluation Setup (Generative Mode):")
print("\nMATH Evaluation Setup (Generative Mode):")
print(f" Dataset: {self.config.dataset_name}")
print(f" Subsets: {self.config.subsets}")
print(f" Evaluation split: {self.config.eval_split}")
@ -484,7 +484,7 @@ class MATHEvalEnv(BaseEnv):
print(f" Format Compliance: {format_valid / total:.2%}")
if self.config.thinking_mode:
print(f" Thinking Utilization: {has_thinking / total:.2%}")
print(f"\n Per-Subset Breakdown:")
print("\n Per-Subset Breakdown:")
for subset, data in sorted(
subset_metrics.items(), key=lambda x: -x[1]["accuracy"]
):
@ -492,7 +492,7 @@ class MATHEvalEnv(BaseEnv):
f" {subset}: {data['accuracy']:.2%} ({data['correct']}/{data['total']})"
)
if level_metrics and len(level_metrics) > 1:
print(f"\n Per-Level Breakdown:")
print("\n Per-Level Breakdown:")
for level, data in sorted(level_metrics.items()):
print(
f" {level}: {data['accuracy']:.2%} ({data['correct']}/{data['total']})"