Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -90,4 +90,17 @@ Nucleus-22B-token-500B was trained on 256 A100 80GB GPUs, using a FSDP
|
|
| 90 |
|
| 91 |
#### Speeds, Sizes, Times
|
| 92 |
|
| 93 |
-
Training happened in early August 2023 and took about two weeks.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
|
| 91 |
#### Speeds, Sizes, Times
|
| 92 |
|
| 93 |
+
Training happened in early August 2023 and took about two weeks.
|
| 94 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 95 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NucleusAI__nucleus-22B-token-500B)
|
| 96 |
+
|
| 97 |
+
| Metric | Value |
|
| 98 |
+
|-----------------------|---------------------------|
|
| 99 |
+
| Avg. | 36.02 |
|
| 100 |
+
| ARC (25-shot) | 40.7 |
|
| 101 |
+
| HellaSwag (10-shot) | 69.39 |
|
| 102 |
+
| MMLU (5-shot) | 30.11 |
|
| 103 |
+
| TruthfulQA (0-shot) | 39.16 |
|
| 104 |
+
| Winogrande (5-shot) | 67.64 |
|
| 105 |
+
| GSM8K (5-shot) | 0.99 |
|
| 106 |
+
| DROP (3-shot) | 4.19 |
|