Add evaluation results on the plain_text config of squad
#1
by
autoevaluator
HF staff
- opened
README.md
CHANGED
@@ -2,4 +2,24 @@
|
|
2 |
license: apache-2.0
|
3 |
datasets:
|
4 |
- squad_v2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
---
|
|
|
2 |
license: apache-2.0
|
3 |
datasets:
|
4 |
- squad_v2
|
5 |
+
model-index:
|
6 |
+
- name: nlpconnect/deberta-v3-xsmall-squad2
|
7 |
+
results:
|
8 |
+
- task:
|
9 |
+
type: question-answering
|
10 |
+
name: Question Answering
|
11 |
+
dataset:
|
12 |
+
name: squad
|
13 |
+
type: squad
|
14 |
+
config: plain_text
|
15 |
+
split: validation
|
16 |
+
metrics:
|
17 |
+
- name: Exact Match
|
18 |
+
type: exact_match
|
19 |
+
value: 84.9246
|
20 |
+
verified: true
|
21 |
+
- name: F1
|
22 |
+
type: f1
|
23 |
+
value: 91.6201
|
24 |
+
verified: true
|
25 |
---
|