Add evaluation results on the plain_text config of squad
#2
by
autoevaluator HF Staff - opened
README.md
CHANGED
|
@@ -66,6 +66,23 @@ model-index:
|
|
| 66 |
type: total
|
| 67 |
value: 11870
|
| 68 |
verified: true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
---
|
| 70 |
|
| 71 |
|
|
|
|
| 66 |
type: total
|
| 67 |
value: 11870
|
| 68 |
verified: true
|
| 69 |
+
- task:
|
| 70 |
+
type: question-answering
|
| 71 |
+
name: Question Answering
|
| 72 |
+
dataset:
|
| 73 |
+
name: squad
|
| 74 |
+
type: squad
|
| 75 |
+
config: plain_text
|
| 76 |
+
split: validation
|
| 77 |
+
metrics:
|
| 78 |
+
- name: Exact Match
|
| 79 |
+
type: exact_match
|
| 80 |
+
value: 84.1741
|
| 81 |
+
verified: true
|
| 82 |
+
- name: F1
|
| 83 |
+
type: f1
|
| 84 |
+
value: 91.0771
|
| 85 |
+
verified: true
|
| 86 |
---
|
| 87 |
|
| 88 |
|