bavest leaderboard-pr-bot commited on
Commit
0082b56
1 Parent(s): 1711452

Adding Evaluation Results (#2)

Browse files

- Adding Evaluation Results (d5433bd2b0ea395c85163cd46241492244753b58)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -144,4 +144,17 @@ You can access the paged optimizer with the argument --optim paged_adamw_32bit
144
  journal = {GitHub repository},
145
  howpublished = {\url{https://github.com/Bavest/fin-llama}},
146
  }
147
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
144
  journal = {GitHub repository},
145
  howpublished = {\url{https://github.com/Bavest/fin-llama}},
146
  }
147
+ ```
148
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
149
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_bavest__fin-llama-33b-merged)
150
+
151
+ | Metric | Value |
152
+ |-----------------------|---------------------------|
153
+ | Avg. | 51.76 |
154
+ | ARC (25-shot) | 65.02 |
155
+ | HellaSwag (10-shot) | 86.2 |
156
+ | MMLU (5-shot) | 58.73 |
157
+ | TruthfulQA (0-shot) | 49.75 |
158
+ | Winogrande (5-shot) | 80.03 |
159
+ | GSM8K (5-shot) | 16.22 |
160
+ | DROP (3-shot) | 6.36 |