mirror of
https://github.com/huggingface/lerobot.git
synced 2026-05-16 09:09:48 +00:00
feat(ci): extract task descriptions and embed in metrics artifact
- Add scripts/ci/extract_task_descriptions.py: runs inside the benchmark Docker container (LIBERO/MetaWorld installed) after lerobot-eval and writes task_descriptions.json mapping task keys to NL instructions. LIBERO: uses libero.libero.benchmark to get suite.get_task(i).language. MetaWorld: formats task name as human-readable label. - Call extraction at the end of each eval bash-c (|| true so never fatal). - parse_eval_metrics.py reads task_descriptions.json and includes it in metrics.json so the health dashboard Space can label videos by task. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -95,6 +95,17 @@ def main() -> int:
|
||||
file=sys.stderr,
|
||||
)
|
||||
|
||||
task_descriptions: dict[str, str] = {}
|
||||
task_desc_path = artifacts_dir / "task_descriptions.json"
|
||||
if task_desc_path.exists():
|
||||
try:
|
||||
task_descriptions = json.loads(task_desc_path.read_text())
|
||||
except json.JSONDecodeError as exc:
|
||||
print(
|
||||
f"[parse_eval_metrics] Warning: could not parse task_descriptions.json: {exc}",
|
||||
file=sys.stderr,
|
||||
)
|
||||
|
||||
metrics = {
|
||||
"env": args.env,
|
||||
"task": args.task,
|
||||
@@ -103,6 +114,7 @@ def main() -> int:
|
||||
"n_episodes": n_episodes,
|
||||
"avg_sum_reward": avg_sum_reward,
|
||||
"eval_s": eval_s,
|
||||
"task_descriptions": task_descriptions,
|
||||
}
|
||||
|
||||
out_path = artifacts_dir / "metrics.json"
|
||||
|
||||
Reference in New Issue
Block a user