Commit
•
65e76d3
1
Parent(s):
0c637d2
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
@@ -19,14 +19,16 @@ model-index:
|
|
19 |
config: squad_v2
|
20 |
split: validation
|
21 |
metrics:
|
22 |
-
-
|
23 |
-
type: exact_match
|
24 |
value: 79.2365
|
|
|
25 |
verified: true
|
26 |
-
|
27 |
-
|
28 |
value: 82.3326
|
|
|
29 |
verified: true
|
|
|
30 |
- task:
|
31 |
type: question-answering
|
32 |
name: Question Answering
|
@@ -36,14 +38,16 @@ model-index:
|
|
36 |
config: adversarialQA
|
37 |
split: test
|
38 |
metrics:
|
39 |
-
-
|
40 |
-
type: exact_match
|
41 |
value: 12.4
|
|
|
42 |
verified: true
|
43 |
-
|
44 |
-
|
45 |
value: 12.4
|
|
|
46 |
verified: true
|
|
|
47 |
- task:
|
48 |
type: question-answering
|
49 |
name: Question Answering
|
@@ -53,14 +57,16 @@ model-index:
|
|
53 |
config: adversarialQA
|
54 |
split: validation
|
55 |
metrics:
|
56 |
-
-
|
57 |
-
type: exact_match
|
58 |
value: 42.3667
|
|
|
59 |
verified: true
|
60 |
-
|
61 |
-
|
62 |
value: 53.3255
|
|
|
63 |
verified: true
|
|
|
64 |
- task:
|
65 |
type: question-answering
|
66 |
name: Question Answering
|
@@ -70,14 +76,16 @@ model-index:
|
|
70 |
config: plain_text
|
71 |
split: validation
|
72 |
metrics:
|
73 |
-
-
|
74 |
-
type: exact_match
|
75 |
value: 86.1925
|
|
|
76 |
verified: true
|
77 |
-
|
78 |
-
|
79 |
value: 92.4306
|
|
|
80 |
verified: true
|
|
|
81 |
---
|
82 |
|
83 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
19 |
config: squad_v2
|
20 |
split: validation
|
21 |
metrics:
|
22 |
+
- type: exact_match
|
|
|
23 |
value: 79.2365
|
24 |
+
name: Exact Match
|
25 |
verified: true
|
26 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmUxNmNjZTg2YzcxMTBkYjE4YTVmODM3YWY2NTFkMmY3NWNiMGYyZTkxZDlkMTJiMjBkZjVhY2NlMGRjYzAyMCIsInZlcnNpb24iOjF9.dn0e2EJ8ImOWODCoRH_d7v10vtxv2ZfRkeWKF-R62sz2ufMjyC9brQihULMw5ZhnSQq5bBFFvauhG6KpLgzgDA
|
27 |
+
- type: f1
|
28 |
value: 82.3326
|
29 |
+
name: F1
|
30 |
verified: true
|
31 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWQyZGNhY2Y3OWE5MTg0ZDM4MmQ0NDk5MjRmODA2OTVmY2ExYTc1MjM2ZTcyNzUxMGI2OWIwMzY5NzMzNzU3NyIsInZlcnNpb24iOjF9.j2Y2sfHayDV5Qfka1bVSbkBIAyMa-rpUxMNICTFvsDVTCnzRPkNVrtrE9dBiDKQa2vVOZNiKrbJEDfXE1xOIBQ
|
32 |
- task:
|
33 |
type: question-answering
|
34 |
name: Question Answering
|
|
|
38 |
config: adversarialQA
|
39 |
split: test
|
40 |
metrics:
|
41 |
+
- type: exact_match
|
|
|
42 |
value: 12.4
|
43 |
+
name: Exact Match
|
44 |
verified: true
|
45 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDExM2Q2NjIxODU4N2FiOWY3NjVjZjNmNzYwYWNhODllMzQxZGVkMzZlMWUzMzJhYTQwMDZhMGQyZjZjNWMyNiIsInZlcnNpb24iOjF9.rMzb2Cna0y3MljrLCRZ8r8SwPFTtwr4OG1mD6gdn3zcVgqX3Td0Q04n_O7RoGuH1788xqEvdeGltd-_TRrC0Aw
|
46 |
+
- type: f1
|
47 |
value: 12.4
|
48 |
+
name: F1
|
49 |
verified: true
|
50 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTNlYjgzMzZlNmYzNjkyYjg4MzYxNTZjZjNkYzA0NTZmNjk5MjI5YzM5YWQ0Y2VlMjVkYWIxNTk2YWJkMTQzYyIsInZlcnNpb24iOjF9.Du89uCtL2-mlV-tewIVKqwG9O53JE3B4Jflpzv4nptpa0MtYiGUAMCunMuWRdBXMe_YdqKDjr7_alJ0-XNRVDQ
|
51 |
- task:
|
52 |
type: question-answering
|
53 |
name: Question Answering
|
|
|
57 |
config: adversarialQA
|
58 |
split: validation
|
59 |
metrics:
|
60 |
+
- type: exact_match
|
|
|
61 |
value: 42.3667
|
62 |
+
name: Exact Match
|
63 |
verified: true
|
64 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmJmYmU5OGFmNjBjNzM1YmRhNDViNDI3MTMwZjg2N2EwYmM2ZDkyZmI4MmY5OGE4NmU5YTA1NThjZDdkYjkyYyIsInZlcnNpb24iOjF9.Iah8AxkCHsDHRTK8SLXzo4qd0C3Ku7bqGVJIJHiPxC2VO3bfz6c5emSSVZk5fACbKYMFoKTeLr6_XTwfTNjGAg
|
65 |
+
- type: f1
|
66 |
value: 53.3255
|
67 |
+
name: F1
|
68 |
verified: true
|
69 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmVlMGFiNjhhOWVjZWUzZTkwOWYzNWQzNjVhNzFhMjRkOGRmNmYwNWIyN2VmZWQ0MDZlNzk0NWM5MzgxMzdhYyIsInZlcnNpb24iOjF9._lW0JTSbvQ-pUBG0cZwpKzCvXMXmjcLrAaxk-bhou_Hf5R3Sw4AEAEy0Vx5qvxk3e30E73mYTInrtBqH8JA3BQ
|
70 |
- task:
|
71 |
type: question-answering
|
72 |
name: Question Answering
|
|
|
76 |
config: plain_text
|
77 |
split: validation
|
78 |
metrics:
|
79 |
+
- type: exact_match
|
|
|
80 |
value: 86.1925
|
81 |
+
name: Exact Match
|
82 |
verified: true
|
83 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWMxYmE4MWRjZDRlMWY3NWMxMjI0YTI5MmVkZTI5OGZiNzM2ZWMyNzlhOGRlNjMzZTBmYWM2OGU0MWM1NDc0MiIsInZlcnNpb24iOjF9.3h6zsLHiqX9ScqvvKhirv4n3S2bP1qpAmnGQrz2eoY0vps2UAN4afyXA_PLMlbk_osgN8Wvnefx74VIgELh6DQ
|
84 |
+
- type: f1
|
85 |
value: 92.4306
|
86 |
+
name: F1
|
87 |
verified: true
|
88 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTVhMWIzYWJhMWNkNzg5NDNlZTdmY2UwNDM3ZWIzZmZjNTA5NDNiMjk2NjI0MTVmNDRjOTYyYjU0YWNmYWE4ZSIsInZlcnNpb24iOjF9.pMkm1BJU1PAsWruRIWhNFrF4DD-nXaE5Gq6sR5mZfQUoeESNWiYGU2GppAvnIEVah0PmdRQHd-DBRK0hDJ2PBg
|
89 |
---
|
90 |
|
91 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|