Results & Artifacts
Where logs, checkpoints, and trajectories land
A run produces several streams of output, all under the repo root (the runtime artifacts are gitignored).
Per-run outputs
| Output | Path | Notes |
|---|---|---|
| Training log | logs/<exp>.log | verl + Harbor integration log (contains the step: metric lines) |
| Throughput log | logs/<exp>_vllm.log | filtered throughput-only log (dashboard skips it) |
| Trajectories | harbor_trials/<project>/<exp>/step_*/<session>/proxy_trajectory.json | per-trial agent traffic (token ids / masks / logprobs) |
| Checkpoints | checkpoints/<project>/<exp>/global_step_N/ | actor FSDP shards, every save_freq steps |
Live state
pgrep -af 'train.sh|fully_async|main_ppo' # is a run live?
tail -F logs/<exp>.log # follow the step lines
ls checkpoints/<project>/<exp>/ # global_step_N/ ...
ls harbor_trials/<project>/<exp>/step_*/ # per-trial trajectoriesvLLM readiness: query the Ray-registered vllm_server_* actors (see
Inference Stack).
Do not commit checkpoints
FSDP shards are large and stay where verl wrote them. Archive metadata and small trajectory samples — never the checkpoints themselves.
Visualizing
The dashboard reads the training logs and renders reward, KL, MFU, entropy, and response-length curves, plus a browser over the per-trial trajectory JSON.