Update .eval_results/gsm8k.yaml
Browse files- .eval_results/gsm8k.yaml +9 -13
.eval_results/gsm8k.yaml
CHANGED
|
@@ -1,13 +1,9 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
- name: exact_match (flexible-extract)
|
| 11 |
-
type: exact_match
|
| 12 |
-
value: 27.67
|
| 13 |
-
verified: false
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: openai/gsm8k
|
| 3 |
+
task_id: gsm8k
|
| 4 |
+
value: 0.2767
|
| 5 |
+
date: "2026-03-19"
|
| 6 |
+
source:
|
| 7 |
+
url: https://github.com/EleutherAI/lm-evaluation-harness
|
| 8 |
+
name: lm-evaluation-harness (5-shot)
|
| 9 |
+
notes: "5-shot, flexible-extract"
|
|
|
|
|
|
|
|
|
|
|
|