Commit
•
3ade81a
1
Parent(s):
1ae8322
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
@@ -1,9 +1,9 @@
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
|
|
4 |
tags:
|
5 |
- question-answering
|
6 |
-
license: apache-2.0
|
7 |
datasets:
|
8 |
- adversarial_qa
|
9 |
- mbartolo/synQA
|
@@ -23,14 +23,16 @@ model-index:
|
|
23 |
config: plain_text
|
24 |
split: validation
|
25 |
metrics:
|
26 |
-
-
|
27 |
-
type: exact_match
|
28 |
value: 89.6529
|
|
|
29 |
verified: true
|
30 |
-
|
31 |
-
|
32 |
value: 94.8172
|
|
|
33 |
verified: true
|
|
|
34 |
- task:
|
35 |
type: question-answering
|
36 |
name: Question Answering
|
@@ -40,14 +42,16 @@ model-index:
|
|
40 |
config: adversarialQA
|
41 |
split: validation
|
42 |
metrics:
|
43 |
-
-
|
44 |
-
type: exact_match
|
45 |
value: 55.3333
|
|
|
46 |
verified: true
|
47 |
-
|
48 |
-
|
49 |
value: 66.7464
|
|
|
50 |
verified: true
|
|
|
51 |
---
|
52 |
|
53 |
# Model Overview
|
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
4 |
+
license: apache-2.0
|
5 |
tags:
|
6 |
- question-answering
|
|
|
7 |
datasets:
|
8 |
- adversarial_qa
|
9 |
- mbartolo/synQA
|
|
|
23 |
config: plain_text
|
24 |
split: validation
|
25 |
metrics:
|
26 |
+
- type: exact_match
|
|
|
27 |
value: 89.6529
|
28 |
+
name: Exact Match
|
29 |
verified: true
|
30 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjM2NTJjZDk0ZWEwM2Q5Njk5NmY5Mzk4ODk4OTViMjZlODlkMTM4M2ZlM2Q0YjgwMWY4OGUzM2QwYTk0YTBhMSIsInZlcnNpb24iOjF9.ZafZxhyJS2xpjYDMhyTO8wVmeZJrwbeJmyvZypMbhUJORR194GJwgttUp150XG3MUFVFqPYQh8tuzpm_QQ6sAA
|
31 |
+
- type: f1
|
32 |
value: 94.8172
|
33 |
+
name: F1
|
34 |
verified: true
|
35 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWE3OGFlYWZmZThhNDMwYzU4OTY3NmU4NmNlYTcwODVkZmQ3N2FlZmE0NGM2Mzk3Nzc2ZmZmNzhkM2NiNzNiMCIsInZlcnNpb24iOjF9.LF4-uxpGMMr7oP_C_SAYHgKMw6I9Sz8FiRnofaD9WFkQZrGPaPR1HjvC6sWo2Nyy5uuD76bowY278Qf8kWwLBw
|
36 |
- task:
|
37 |
type: question-answering
|
38 |
name: Question Answering
|
|
|
42 |
config: adversarialQA
|
43 |
split: validation
|
44 |
metrics:
|
45 |
+
- type: exact_match
|
|
|
46 |
value: 55.3333
|
47 |
+
name: Exact Match
|
48 |
verified: true
|
49 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmIwZTdmNzg4MmE5YjM2MzkxOWFmM2JmODMzZDhhZGY5YWE0Njc2MmY0YzIyNzEwMGU0MDIwOTZjZTEyZjk5YSIsInZlcnNpb24iOjF9.dNd-MElaXPRrYSgvzxcMyN87ts0iyON4mdQChv68AIspmQKAUKRVzdm7w0mhRyvzG8a7aDl7dgUFCZVxd7-FAQ
|
50 |
+
- type: f1
|
51 |
value: 66.7464
|
52 |
+
name: F1
|
53 |
verified: true
|
54 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDU4ZTE0MTliNmJjYmFjZmI4MjEwMWRiMjJmZjhjYzBkY2Q0ZGUzMzZlMTZkNmFlZThmYzMyMThjN2IwMjI3NSIsInZlcnNpb24iOjF9.A4AxMaEXNDRZaR_ZazFH3PUhi-jn0JniWv7xEXGM3oidhR6hsWNi5twqegAAuZe56YDPxCUhuoGahovcWmoaBQ
|
55 |
---
|
56 |
|
57 |
# Model Overview
|