---
license: apache-2.0
---

# pythia-12b-sft-v8-rlhf-2k-steps

- sampling report: [2023-05-15_OpenAssistant_pythia-12b-sft-v8-rlhf-2k-steps_sampling_noprefix2.json](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-rl%2F2023-05-15_OpenAssistant_pythia-12b-sft-v8-rlhf-2k-steps_sampling_noprefix2.json)
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_OpenAssistant__pythia-12b-sft-v8-rlhf-2k-steps)

| Metric                | Value                     |
|-----------------------|---------------------------|
| Avg.                  | 36.36   |
| ARC (25-shot)         | 43.43          |
| HellaSwag (10-shot)   | 70.08    |
| MMLU (5-shot)         | 26.12         |
| TruthfulQA (0-shot)   | 36.06   |
| Winogrande (5-shot)   | 64.64   |
| GSM8K (5-shot)        | 9.55        |
| DROP (3-shot)         | 4.63         |