Vlm captcha train

[shannonsands]

PR Type

• RL Environment PR - Complete Environment Snapshot & Zero-Training sections
• Non-Environment PR - Complete Description, Related Issues & Type of Change sections

---

📝 General Information

Description

RLVR on number captchas

🔖 Environment Snapshot

Field	Your Entry
Environment Name	CaptchaEnv
Short Description	RLVR on numeric captcha dataset
Category	Verifiable-Reasoning
Dataset Needed?	Yes: https://huggingface.co/datasets/project-sloth/captcha-images, WTFPL
External Deps	None (covered by other multimodal envs)
Environmental Variables
Compute Footprint Estimate	2 nodes works on small models

🧪 Zero-Training Test Results

Details

W&B Link:

Examples of the Environment scoring a good example and a bad example:

---

✅ Developer & Reviewer Checklist

• Code follows project style (black, isort, flake8 pass with pre-commit)
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• New and existing unit tests pass locally with my changes
• Docstrings added for all new public classes / functions
• If .env vars required, did you add it to the .env.example in repo root?

[shannonsands]

Needs testing on cluster

[teknium1]

@shannonsands is this ready to merge xD