Results & Artifacts

Everything a job produces lands under this block's artifacts/ directory. This page maps out what is written and where.

Per-job outputs

artifacts/jobs/<job>/
├── result.json                              # aggregate job stats (rewards, errors, evals)
├── config.yaml                              # snapshot of the active config at launch
└── <task>/agent/litellm-trajectory.jsonl    # one raw trajectory per task

• litellm-trajectory.jsonl is the primary output: the replayable log of one rollout, consumed by the sft block and by SFT conversion.
• result.json aggregates rewards and error stats across all rollouts; it is what the dashboard reads.

This directory is the block's raw_trajectories_dir output (declared in config.yaml → runtime_info.output), consumed downstream by sft.

SFT data outputs

When conversion runs (automatically when sft_conversion.enabled is true, or manually via scripts/convert_trajectories.sh), it writes:

artifacts/sft_data/<job>/
├── im.jsonl        # intermediate OpenAI-style messages, auto-scored
├── lf.json         # LLaMA-Factory ShareGPT array (the sft block's input)
└── lf.stats.json   # token/turn/score statistics for the dashboard

This is the block's sft_data_dir output. See SFT Data for the conversion pipeline.

Run archives

After each run, a snapshot is archived under:

artifacts/archives/run_NNN/
├── metadata.yaml   # run id, timestamps, results, repo commit ids, copy of inputs
├── config.yaml     # config as it was at run time
├── scripts/        # copy of executed scripts
├── session.log     # session record
└── monitor.md      # monitor output

and one entry is appended to artifacts/index.yaml. Use artifacts/index.yaml for archived run history and config.yaml → status for the current operational snapshot (see Status).

Cleaning up

scripts/clean.sh removes gitignored runtime outputs, including artifacts/sft_data, dashboard/site/, and the dashboard cache. It does not touch archived runs.