rl-standard-launch-leonardo

rl-standard-launch-leonardo is a Model training & evaluation skill for AI agents, published by open-thoughts in the OpenThoughts-Agent repository on GitHub. Skillspace rates rl-standard-launch-leonardo D (55/100) and it passed the safety scan; the rating is based on static analysis only.

Launch, relaunch, or sweep STANDARD (non-agentic) SkyRL RL on CINECA Leonardo — GRPO on math/reasoning datasets (gsm8k, MATH/aime) and on-policy distillation (OPD, teacher→student) — via raw `sbatch` of the `hpc/skyrl_standard/leonardo/*` run scripts inside the writable apptainer SANDBOX + uv `marin_venv` (NOT `python -m hpc.launch`, NOT a `.sif`, NOT `--rl_use_conda`). Use when asked to run/relaunch a gsm8k or OPD GRPO canary, throughput/accuracy grid, or multi-node RL on Leonardo A100-64GB. Covers the GRPO/OPD knobs, the grid cell structure, the 1-node-vs-multi-node layout, the A100-64GB ceilings, and the no-internet/offline + gcc/HOME/Ray-temp-dir gotchas. For agentic Harbor+Daytona RL, this is the WRONG skill (Daytona needs internet — infeasible on Leonardo).

Grade

D

Quality

55 / 100

Safety

Passed

GitHub stars

259

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.