Commit
•
9bf0ac5
1
Parent(s):
3528ea1
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator
Browse filesBeep boop, I am a bot from Hugging Face's automatic model evaluator 👋! We've added a new `verifyToken` field to your evaluation results to verify that they are produced by the model evaluator. Accept this PR to ensure that your results remain listed as **verified** on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards).
README.md
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
---
|
2 |
language: en
|
3 |
-
datasets:
|
4 |
-
- squad_v2
|
5 |
license: cc-by-4.0
|
6 |
tags:
|
7 |
- deberta
|
8 |
- deberta-v3
|
|
|
|
|
9 |
model-index:
|
10 |
- name: deepset/deberta-v3-base-squad2
|
11 |
results:
|
@@ -18,14 +18,16 @@ model-index:
|
|
18 |
config: squad_v2
|
19 |
split: validation
|
20 |
metrics:
|
21 |
-
-
|
22 |
-
type: exact_match
|
23 |
value: 83.8248
|
|
|
24 |
verified: true
|
25 |
-
|
26 |
-
|
27 |
value: 87.41
|
|
|
28 |
verified: true
|
|
|
29 |
- task:
|
30 |
type: question-answering
|
31 |
name: Question Answering
|
@@ -35,14 +37,16 @@ model-index:
|
|
35 |
config: plain_text
|
36 |
split: validation
|
37 |
metrics:
|
38 |
-
-
|
39 |
-
type: exact_match
|
40 |
value: 84.9678
|
|
|
41 |
verified: true
|
42 |
-
|
43 |
-
|
44 |
value: 92.2777
|
|
|
45 |
verified: true
|
|
|
46 |
---
|
47 |
|
48 |
# deberta-v3-base for QA
|
|
|
1 |
---
|
2 |
language: en
|
|
|
|
|
3 |
license: cc-by-4.0
|
4 |
tags:
|
5 |
- deberta
|
6 |
- deberta-v3
|
7 |
+
datasets:
|
8 |
+
- squad_v2
|
9 |
model-index:
|
10 |
- name: deepset/deberta-v3-base-squad2
|
11 |
results:
|
|
|
18 |
config: squad_v2
|
19 |
split: validation
|
20 |
metrics:
|
21 |
+
- type: exact_match
|
|
|
22 |
value: 83.8248
|
23 |
+
name: Exact Match
|
24 |
verified: true
|
25 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2IyZTEyYzNlOTAwZmFlNWRiZTdiNzQzMTUyM2FmZTQ3ZWQwNWZmMzc2ZDVhYWYyMzkxOTUyMGNlMWY0M2E5MiIsInZlcnNpb24iOjF9.y8KvfefMLI977BYun0X1rAq5qudmezW_UJe9mh6sYBoiWaBosDO5TRnEGR1BHzdxmv2EgPK_PSomtZvb043jBQ
|
26 |
+
- type: f1
|
27 |
value: 87.41
|
28 |
+
name: F1
|
29 |
verified: true
|
30 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWVhNjAwM2Q5N2Y3MGU4ZWY3N2Y0MmNjYWYwYmQzNTdiYWExODhkYmQ1YjIwM2I1ODEzNWIxZDI1ZWQ1YWRjNSIsInZlcnNpb24iOjF9.Jk0v1ZheLRFz6k9iNAgCMMZtPYj5eVwUCku4E76wRYc-jHPmiUuxvNiNkn6NW-jkBD8bJGMqDSjJyVpVMn9pBA
|
31 |
- task:
|
32 |
type: question-answering
|
33 |
name: Question Answering
|
|
|
37 |
config: plain_text
|
38 |
split: validation
|
39 |
metrics:
|
40 |
+
- type: exact_match
|
|
|
41 |
value: 84.9678
|
42 |
+
name: Exact Match
|
43 |
verified: true
|
44 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWUxYTg4MzU3YTdmMDRmMGM0NjFjMTcwNGM3YzljM2RkMTc1ZGNhMDQwMTgwNGI0ZDE4ZGMxZTE3YjY5YzQ0ZiIsInZlcnNpb24iOjF9.KKaJ1UtikNe2g6T8XhLoWNtL9X4dHHyl_O4VZ5LreBT9nXneGc21lI1AW3n8KXTFGemzRpRMvmCDyKVDHucdDQ
|
45 |
+
- type: f1
|
46 |
value: 92.2777
|
47 |
+
name: F1
|
48 |
verified: true
|
49 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDU0ZTQwMzg4ZDY1ZWYxOGIxMzY2ODljZTBkMTNlYjA0ODBjNjcxNTg3ZDliYWU1YTdkYTM2NTIxOTg1MGM4OCIsInZlcnNpb24iOjF9.8VHg1BXx6gLw_K7MUK2QSE80Y9guiVR8n8K8nX4laGsLibxv5u_yDv9F3ahbUa1eZG_bbidl93TY2qFUiYHtAQ
|
50 |
---
|
51 |
|
52 |
# deberta-v3-base for QA
|