Commit
路
1b55357
1
Parent(s):
c9d9ed1
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 馃憢! 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: adversarialQA
|
20 |
split: validation
|
21 |
metrics:
|
22 |
-
-
|
23 |
-
type: exact_match
|
24 |
value: 42.9
|
|
|
25 |
verified: true
|
26 |
-
|
27 |
-
|
28 |
value: 53.8954
|
|
|
29 |
verified: true
|
|
|
30 |
- task:
|
31 |
type: question-answering
|
32 |
name: Question Answering
|
@@ -36,14 +38,16 @@ model-index:
|
|
36 |
config: squad_v2
|
37 |
split: validation
|
38 |
metrics:
|
39 |
-
-
|
40 |
-
type: exact_match
|
41 |
value: 79.5382
|
|
|
42 |
verified: true
|
43 |
-
|
44 |
-
|
45 |
value: 82.7221
|
|
|
46 |
verified: true
|
|
|
47 |
- task:
|
48 |
type: question-answering
|
49 |
name: Question Answering
|
@@ -53,14 +57,16 @@ model-index:
|
|
53 |
config: default
|
54 |
split: validation
|
55 |
metrics:
|
56 |
-
-
|
57 |
-
type: exact_match
|
58 |
value: 78.403
|
|
|
59 |
verified: true
|
60 |
-
|
61 |
-
|
62 |
value: 82.1408
|
|
|
63 |
verified: true
|
|
|
64 |
---
|
65 |
|
66 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
19 |
config: adversarialQA
|
20 |
split: validation
|
21 |
metrics:
|
22 |
+
- type: exact_match
|
|
|
23 |
value: 42.9
|
24 |
+
name: Exact Match
|
25 |
verified: true
|
26 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODRhNDM3Y2RlYzgyMzQ3MDdlMzc1YmFmNjFkYjYzODFiNjU4Mzg5YmZkMTI0N2U5NTAyMTA2ODQ4MmY5Mzc3MiIsInZlcnNpb24iOjF9.jFyNzcBNLdKPZJHtcwmSE_rgT9nT1EavaleEGtB1U9fA2iGkjUFeWcF539mNrUSzfObj5tCbNWgHGASa7gPQDA
|
27 |
+
- type: f1
|
28 |
value: 53.8954
|
29 |
+
name: F1
|
30 |
verified: true
|
31 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDQ3MzhmMTcxYmM0ZjA2MjgwNjJkYTU5NDkyMGNiZjZiMDc2MzZhOTM2ZWM3ZDIwMjg0ODlmNGZkNWU3ODkyNyIsInZlcnNpb24iOjF9.8eXunF16sRKtW0tfSBMFjKA2LUVPzgIxkjQ1d2qz0FyEYA7PM0Zp5DJ_WhlIowbvjKAe5YQOV-ACCksS-_43Bw
|
32 |
- task:
|
33 |
type: question-answering
|
34 |
name: Question Answering
|
|
|
38 |
config: squad_v2
|
39 |
split: validation
|
40 |
metrics:
|
41 |
+
- type: exact_match
|
|
|
42 |
value: 79.5382
|
43 |
+
name: Exact Match
|
44 |
verified: true
|
45 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmI4M2I4MDJiMWYzNjE0YmU2OGNmZjU5ZDA5MzM4ODhlZjNkMjMyOTQ4YTlkYzdjMGYzN2U5N2IyOGQwM2QzMCIsInZlcnNpb24iOjF9.vQ0xbOhNvzMXefT2VKpDdCzIFj80KxFD3fVk_qNaPH9TzHw5Vu1rBx6GVePsYblSV7-VwR20WMuKsitRNRrMAA
|
46 |
+
- type: f1
|
47 |
value: 82.7221
|
48 |
+
name: F1
|
49 |
verified: true
|
50 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjBiN2I3YzE5OTQwZTg4NDE4MjBiODY1ZDQwMzYwNmY0MTA5NzJlNTg0NmEyNDJkZjRhM2IyZWM3MDQ3NGU3OSIsInZlcnNpb24iOjF9.QMaxPxW1SU-240Qx_aNr6BWTJ67nEy_abhgTmrIk4PreH5EbH13H8Kn3u21p85XmDNMPBxE-uh2mR57x1bjJAg
|
51 |
- task:
|
52 |
type: question-answering
|
53 |
name: Question Answering
|
|
|
57 |
config: default
|
58 |
split: validation
|
59 |
metrics:
|
60 |
+
- type: exact_match
|
|
|
61 |
value: 78.403
|
62 |
+
name: Exact Match
|
63 |
verified: true
|
64 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTY1NzA2NWQ2YTgxOWNjNGM5MTc5ODVmMjI5NGIxZjZlOGQxYzUzNDI0YzgyNjdiYjhjMDc0NmY5YTZkZjg4YiIsInZlcnNpb24iOjF9.PyLmsoXlKaTryvr1L7SGp9tBMyKwe9YDodYjXBw1sA2F-AHts_G9RPljx0ujFYbp7mcVuTKkzeQ3mGHZpG0eCw
|
65 |
+
- type: f1
|
66 |
value: 82.1408
|
67 |
+
name: F1
|
68 |
verified: true
|
69 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjE2MzY5NzFhYWVhMzJmNWYyOWQzYjJjNjk5OWNkZWMwODNiNmIwMmQwMzcwYmEwZjBjNGZhYmI2OGNkMTk0YSIsInZlcnNpb24iOjF9.9dRYfF2mLRsUCD5uTE9h1vfSSMFzDmjVkFEAjl0h1BSaNUCxLk6aDMeYin3qi7kG4SEeqrRycg_Cc0gGUQmmDg
|
70 |
---
|
71 |
|
72 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|