pszemraj leaderboard-pr-bot commited on
Commit
056b148
1 Parent(s): 6eeded6

Adding Evaluation Results (#3)

Browse files

- Adding Evaluation Results (c3a9b408f7e6f92d4394d662e71f4551786d383e)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -143,4 +143,17 @@ The following hyperparameters were used during training:
143
  - Transformers 4.27.0.dev0
144
  - Pytorch 1.13.1+cu117
145
  - Datasets 2.8.0
146
- - Tokenizers 0.13.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
143
  - Transformers 4.27.0.dev0
144
  - Pytorch 1.13.1+cu117
145
  - Datasets 2.8.0
146
+ - Tokenizers 0.13.1
147
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
148
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_postbot__pythia-160m-hq-emails)
149
+
150
+ | Metric | Value |
151
+ |-----------------------|---------------------------|
152
+ | Avg. | 25.12 |
153
+ | ARC (25-shot) | 23.12 |
154
+ | HellaSwag (10-shot) | 30.05 |
155
+ | MMLU (5-shot) | 26.58 |
156
+ | TruthfulQA (0-shot) | 45.51 |
157
+ | Winogrande (5-shot) | 50.28 |
158
+ | GSM8K (5-shot) | 0.0 |
159
+ | DROP (3-shot) | 0.31 |