Dashboard
Watch reward, KL, MFU, and response length live
LiveRL ships a self-contained training dashboard (webui/) that reads your run
logs and renders live metric charts, a run comparison view, an agent-trajectory
browser, and optional LLM analysis — open it locally or over a public tunnel.
Live board: valves-profit-theaters-midwest.trycloudflare.com
Tunnel URLs are ephemeral
The link above is a Cloudflare quick tunnel opened by start_dashboard.sh
(TUNNEL=true); the URL changes each time the tunnel restarts. For a stable
public URL, deploy the frontend to a Cloudflare Pages project instead.
What it monitors
webui/server.py discovers .log/.out files under the log dir (skipping
*_vllm.log) as runs and parses the verl step:N - key:value - ... lines,
cleaning numpy wrappers like np.float64(...). Point it at:
| Source | Path |
|---|---|
| Training logs | logs/<exp>.log |
| Any extra log dir | via --extra-log-dir |
For each run it surfaces the full per-step metric set — reward (critic/score/mean),
actor/entropy, actor/ppo_kl, actor/pg_clipfrac, perf/mfu/*,
response_length/*, rollout_corr/kl, and val-* — plus a trajectory browser
over the per-trial harbor_trials/ logs.
Run it locally
bash webui/start_dashboard.shThis builds the frontend if dist/ is missing, starts the API server on
:8090 (reading ../logs), and — with TUNNEL=true (default) — opens a
Cloudflare quick tunnel and prints the public URL. Then open http://<host-ip>:8090.
Override the server directly:
python3 webui/server.py --port 8090 --log-dir logs --static-dir webui/dist \
[--extra-log-dir <dir>] [--wandb-entity <e> --wandb-project <p> --wandb-api-key <k>]PORT, LOG_DIR, and TUNNEL are also honored as env vars by
start_dashboard.sh (see webui/README.md).
Data sources
The local server reads your log files; if wandb credentials are supplied it
can additionally surface runs from the wandb API. A Cloudflare Pages deployment
(webui/functions/api/[[path]].ts) reads runs/metrics straight from wandb and
does not see local log files — so a published board reflects the configured
wandb project, while the local server reads your launch logs.