Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator
#1
by
autoevaluator
HF staff
- opened
README.md
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
---
|
2 |
-
datasets:
|
3 |
-
- squad_v2
|
4 |
language: en
|
5 |
license: mit
|
6 |
-
pipeline_tag: question-answering
|
7 |
tags:
|
8 |
- deberta
|
9 |
- deberta-v3
|
|
|
|
|
|
|
10 |
model-index:
|
11 |
- name: navteca/deberta-v3-base-squad2
|
12 |
results:
|
@@ -19,14 +19,16 @@ model-index:
|
|
19 |
config: squad_v2
|
20 |
split: validation
|
21 |
metrics:
|
22 |
-
-
|
23 |
-
type: exact_match
|
24 |
value: 88.0876
|
|
|
25 |
verified: true
|
26 |
-
|
27 |
-
|
28 |
value: 91.1623
|
|
|
29 |
verified: true
|
|
|
30 |
- task:
|
31 |
type: question-answering
|
32 |
name: Question Answering
|
@@ -36,14 +38,16 @@ model-index:
|
|
36 |
config: plain_text
|
37 |
split: validation
|
38 |
metrics:
|
39 |
-
-
|
40 |
-
type: exact_match
|
41 |
value: 89.2366
|
|
|
42 |
verified: true
|
43 |
-
|
44 |
-
|
45 |
value: 95.0569
|
|
|
46 |
verified: true
|
|
|
47 |
---
|
48 |
|
49 |
# Deberta v3 large model for QA (SQuAD 2.0)
|
|
|
1 |
---
|
|
|
|
|
2 |
language: en
|
3 |
license: mit
|
|
|
4 |
tags:
|
5 |
- deberta
|
6 |
- deberta-v3
|
7 |
+
datasets:
|
8 |
+
- squad_v2
|
9 |
+
pipeline_tag: question-answering
|
10 |
model-index:
|
11 |
- name: navteca/deberta-v3-base-squad2
|
12 |
results:
|
|
|
19 |
config: squad_v2
|
20 |
split: validation
|
21 |
metrics:
|
22 |
+
- type: exact_match
|
|
|
23 |
value: 88.0876
|
24 |
+
name: Exact Match
|
25 |
verified: true
|
26 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWRmMDg2ZjQ4ZjhhOWIzZjRhNTU2ZGFjZGM3NGY5MzBkYzk2MWU2Y2M1ODcxYjcxMTBkOTM0MGYwNzVlMmEwOCIsInZlcnNpb24iOjF9.bQdENVyV5sMVHiBQZX5yp0dSUWnd23-oLG1qdAdoMzGHxP3cq_RBcmhQ7Qpe6MC-UfcAuLedhs7ERAGX1OaaBw
|
27 |
+
- type: f1
|
28 |
value: 91.1623
|
29 |
+
name: F1
|
30 |
verified: true
|
31 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmEyY2RhYzAzNzYwM2ZhNjUyOWZjNzYzZDk0YmU4ZGQwZWZkYTNlYzBkZDdiZGY4YTI3MTI5MGMyZjgzYmI5YyIsInZlcnNpb24iOjF9.T9wVVp4RW76X5tdm0l3WzqtHX6bWuRc-OtIKTtHVPoauzNR4Tt3Q0LeR-_tOsOiTVCEV6A-3np43BQ2Zobk6Cg
|
32 |
- task:
|
33 |
type: question-answering
|
34 |
name: Question Answering
|
|
|
38 |
config: plain_text
|
39 |
split: validation
|
40 |
metrics:
|
41 |
+
- type: exact_match
|
|
|
42 |
value: 89.2366
|
43 |
+
name: Exact Match
|
44 |
verified: true
|
45 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjRmNGE5MzQzOGFmMjhmMTc4NDMxYjVmMjRmZTRjYjQyMTNiOTgzNWQ2YTQ5NjFhNjk2ZjdlNDMxNDljM2QwZiIsInZlcnNpb24iOjF9.5_WAX03-LTeIrmMkQQgNZc5Iqo-VH3WJYmK0ydNfa3O7JJymc0aQncbG3AHDT85K5HY5tygS4DKmwQ0U2vajAA
|
46 |
+
- type: f1
|
47 |
value: 95.0569
|
48 |
+
name: F1
|
49 |
verified: true
|
50 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTExMGY3YzcyYjRmZWU0YjU2ZjIzMTViMzk4YzRmNmY1NWMxZGU3MGVlNWE1NmJiZmVjZjRmYjBlZWU4Mjg5MCIsInZlcnNpb24iOjF9.m5PEInPwVxTusAzfl3AUbDFAbeu9Oywb8gVHsOtc5paKe5ePN3VhXeu7YPGufYbLETqiaueRS5t4fulPH2CFAA
|
51 |
---
|
52 |
|
53 |
# Deberta v3 large model for QA (SQuAD 2.0)
|