You can deploy this model and start earning money today!

jayshah5696/
humanize-p5050-qwen35-2b-base-full400-env0315-r1

Name: humanize-p5050-qwen35-2b-base-full400-env0315-r1
Availability: InStock

prime-intellect

reinforcement-learning

Views

No views yet

humanize-p5050-qwen35-2b-base-full400-env0315-r1

Prime Hosted RL run for Qwen/Qwen3.5-2B on jayshah5696/humanize-rl-env@0.3.15.

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.

Main result

Final step 400:

mix p50 avg@1: 0.7093008879222907
v02 strict avg@1: 0.43871350751982796
v03 strict avg@1: 0.124382966841523

Best mix checkpoint was step 350:

mix p50 avg@1: 0.717125491476916
Prime adapter id: v8bin4fqkl5glsfe9h7g8vr0

Final Prime adapter id:

step 400 adapter id: wxhjhfx6hc7xzuqbneinr7zr
run id: ln8ui3bmtx4skvxcu7pwvvbl

Important caveat

Metrics 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.md
eval_summary.json
usage.json
checkpoints.json
adapters.json
before_after_examples.json
rollout samples every 10 steps from 0 through 390

jayshah5696/humanize-p5050-qwen35-2b-base-full400-env0315-r1

humanize-p5050-qwen35-2b-base-full400-env0315-r1

Main result

Important caveat

Contents

jayshah5696/
humanize-p5050-qwen35-2b-base-full400-env0315-r1