PaulR11/training-runs-intragroup-nofp download history

PaulR11/training-runs-intragroup-nofp is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 11 times (4 in the last 7 days), and 1,693 times in total. It ranks #541,719 among datasets by monthly downloads.

GRPO Training Runs — Intragroup Pairwise Without FP Calibration Part of the data release for "Training Alignment Auditors via Reinforcement Learning" (ICLR 2026). Two no-FP-calibration intragroup runs. Target: Llama 3.3 70B (OpenRouter). ig_pv2_grpo_intragroup_petri_v2/ — canonical Petri

Open PaulR11/training-runs-intragroup-nofp on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.