HF RL Explorer

Repair scalar and array result normalization in three vendored Evaluate classification metrics.

Repair scalar and array result normalization in three vendored Evaluate classification metrics.: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). Repair the evaluation metric boundary The workspace contains a frozen slice of a Hugging Face Evaluate repository under…

The task

Repair the evaluation metric boundary The workspace contains a frozen slice of a Hugging Face Evaluate repository under /app/vendor/project. Its precision, recall, and F1 metric scripts call scikit-learn and then normalize the returned score for downstream JSON serialization.…

Part of XiaomiMiMo/MiMo-V2.6-RL-oss.