grug-67b-a2b-snowball-post-sft-evals

# Grug 67B-A2B Snowball Post-SFT Evaluation Artifacts This repository contains the raw output bundle for the evaluation reported in [`marin-community/marin` issue #7505](https://github.com/marin-community/marin/issues/7505). It contains `287` score JSON files and `240` sample JSONL files (about 1.4 GB), preserving the layout created by the evaluation jobs. `RESULTS.md` is the harvested result table. `POLICY.md`, `LAUNCHER.md`, `launch_baseline.sh`, and `harvest_s3.py` document the evaluation and harvest workflow. The evaluated checkpoint is [`penfever/grug-67b-a2b-sft-s2-thinking-step630`](https://huggingface.co/penfever/grug-67b-a2b-sft-s2-thinking-step630). The artifacts are provided for inspection and reproduction. They contain model outputs and benchmark results; please observe the licenses and terms of the underlying models and benchmarks.