Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -69,3 +69,17 @@ with torch.autocast('cuda', dtype=torch.bfloat16):
|
|
69 |
| Optimizer | Lion |
|
70 |
| Learning rate | 2e-4 |
|
71 |
| Batch size | 1024 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
| Optimizer | Lion |
|
70 |
| Learning rate | 2e-4 |
|
71 |
| Batch size | 1024 |
|
72 |
+
|
73 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
74 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_team-lucid__mptk-1b)
|
75 |
+
|
76 |
+
| Metric | Value |
|
77 |
+
|-----------------------|---------------------------|
|
78 |
+
| Avg. | 17.88 |
|
79 |
+
| ARC (25-shot) | 22.7 |
|
80 |
+
| HellaSwag (10-shot) | 25.48 |
|
81 |
+
| MMLU (5-shot) | 27.11 |
|
82 |
+
| TruthfulQA (0-shot) | 0.0 |
|
83 |
+
| Winogrande (5-shot) | 49.72 |
|
84 |
+
| GSM8K (5-shot) | 0.0 |
|
85 |
+
| DROP (3-shot) | 0.17 |
|