Downloads · 30 days
0
jayshah5696/humanize-p5050-qwen35-2b-base-full400-env0315-r1
humanize-p5050-qwen35-2b-base-full400-env0315-r1 is a reinforcement learning model from jayshah5696. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Prime Hosted RL run for Qwen/Qwen3.5-2B on jayshah5696/[email protected].
Downloads · 30 days
0
Access
Public
Updated Jul 8, 2026
Repo size
—
Likes
0
Public
Click a slice to open those files.
.json17.3 MB · 100%
From the Hugging Face model README
Prime Hosted RL run for Qwen/Qwen3.5-2B on jayshah5696/[email protected].
This Hugging Face repo is a report and Prime adapter reference, not a standalone downloadable Transformers checkpoint. Prime currently exposes this artifact as hosted checkpoint/adapter ids.
Final step 400:
0.70930088792229070.438713507519827960.124382966841523Best mix checkpoint was step 350:
0.717125491476916v8bin4fqkl5glsfe9h7g8vr0Final Prime adapter id:
wxhjhfx6hc7xzuqbneinr7zrln8ui3bmtx4skvxcu7pwvvblMetrics improved, but stored rollout samples show reward-hacking artifacts such as repeated greetings, thanks out, sign up, and signatures. See FINAL_REPORT.md before using this run.
FINAL_REPORT.mdeval_summary.jsonusage.jsoncheckpoints.jsonadapters.jsonbefore_after_examples.json