{
 "schema_version": 1,
 "generated": "2026-10-31",
 "id": "eleutherai-lm-evaluation-harness--save-and-share-lm-eval-results",
 "repo": "EleutherAI/lm-evaluation-harness",
 "repo_url": "https://github.com/EleutherAI/lm-evaluation-harness",
 "repo_slug": "eleutherai-lm-evaluation-harness",
 "title": "Keep every eval run reproducible and shareable",
 "page_title": "How to keep every eval run reproducible and shareable with LM Evaluation Harness",
 "summary": "Write results and per sample responses to disk, cache repeat runs and push the results to the Hub.",
 "who": "A team tracking model quality over many runs.",
 "problem": "Scores pasted into chat cannot be audited later.",
 "outcome": "Saved results plus logged samples you can diff and share.",
 "steps": [
  "Install the harness and your backend extra as in the installation section",
  "Add `--output_path results` to save the results of a run",
  "Add `--log_samples` to log model responses for post-hoc analysis",
  "Speed up resumed runs with `--use_cache <DIR>`, and push to the Hub with `--hf_hub_log_args` after setting a write token in HF_TOKEN"
 ],
 "agent_prompt": "Using EleutherAI/lm-evaluation-harness, rerun my evaluation with --output_path and --log_samples, then show me how to diff two runs' sample outputs.",
 "agents": [
  "claude-code",
  "codex",
  "cursor",
  "gemini-cli"
 ],
 "difficulty": "Intermediate",
 "time": "1 hour",
 "basis": "readme",
 "caveat": "Caching is rank dependent, so resume an interrupted run with the same GPU count.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "",
 "requirements": [
  "Python with pip; the base package no longer includes transformers or torch",
  "A model backend extra such as `pip install \"lm_eval[hf]\"`, `pip install \"lm_eval[vllm]\"` or `pip install \"lm_eval[api]\"`",
  "A CUDA GPU for the local model examples, which pass --device cuda:0",
  "An API key in the environment for hosted models"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "credentials",
   "notice": "Pushing to the Hub needs an access token with write access in HF_TOKEN."
  }
 ],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/eleutherai-lm-evaluation-harness/save-and-share-lm-eval-results/",
 "md": "https://dedupedai.com/use-cases/eleutherai-lm-evaluation-harness/save-and-share-lm-eval-results/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/eleutherai-lm-evaluation-harness--save-and-share-lm-eval-results.json",
 "api_version": "v1"
}