Fix task_id to diamond (matching benchmark eval.yaml)
Browse files- .eval_results/gpqa.yaml +2 -1
.eval_results/gpqa.yaml
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
- dataset:
|
| 2 |
id: Idavidrein/gpqa
|
| 3 |
-
task_id:
|
| 4 |
value: 71.5
|
| 5 |
date: '2026-01-27'
|
| 6 |
source:
|
| 7 |
url: https://huggingface.co/deepseek-ai/DeepSeek-R1
|
| 8 |
name: Model Card
|
|
|
|
|
|
| 1 |
- dataset:
|
| 2 |
id: Idavidrein/gpqa
|
| 3 |
+
task_id: diamond
|
| 4 |
value: 71.5
|
| 5 |
date: '2026-01-27'
|
| 6 |
source:
|
| 7 |
url: https://huggingface.co/deepseek-ai/DeepSeek-R1
|
| 8 |
name: Model Card
|
| 9 |
+
user: burtenshaw
|