training

star 1.5k

Launch and monitor prime-rl training runs. Use when starting, supervising, or debugging an RL/SFT run. Routes to `start-run` (entrypoints + how to launch) and `monitor-run` (logs, metrics, check-ins).

By PrimeIntellect-ai schedule Updated 6/3/2026

play_arrow Run Skill in Manus View GitHub

name: training description: Launch and monitor prime-rl training runs. Use when starting, supervising, or debugging an RL/SFT run. Routes to `start-run` (entrypoints + how to launch) and `monitor-run` (logs, metrics, check-ins).

Training

Two phases — start the run, then watch it.

Start a run — see start-run/SKILL.md for the rl, sft, and inference entrypoints and how to launch them (single-node, SLURM, dry-run).
Monitor a run — see monitor-run/SKILL.md for the runbook: how to find the output dir, what to tail, which metrics to watch, and how to restart safely.

Both subskills assume the configs skill for config-loading mechanics.

Install via CLI

npx skills add https://github.com/PrimeIntellect-ai/prime-rl --skill training

Repository Details

star Stars 1,484

call_split Forks 313

navigation Branch main

article Path SKILL.md

Occupations

Data Scientists 152051

training

name: training description: Launch and monitor prime-rl training runs. Use when starting, supervising, or debugging an RL/SFT run. Routes to start-run (entrypoints + how to launch) and monitor-run (logs, metrics, check-ins).

Training

name: training description: Launch and monitor prime-rl training runs. Use when starting, supervising, or debugging an RL/SFT run. Routes to `start-run` (entrypoints + how to launch) and `monitor-run` (logs, metrics, check-ins).