Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#3)

- Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (a8bbb794792872125fa14ca84d76b950fa0acccb)


Co-authored-by: Evaluation Bot <[email protected]>

README.md

@@ -1,5 +1,13 @@
 ---
+language: en
 license: cc-by-4.0
+tags:
+- question-answering
+datasets:
+- squad_v2
+metrics:
+- f1
+- exact
 widget:
 - context: DeBERTa improves the BERT and RoBERTa models using disentangled attention
     and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa
@@ -21,30 +29,22 @@ widget:
     for more implementation details and updates.
   example_title: DeBERTa v3 Q2
   text: Where do I go to see new info about DeBERTa?
-datasets:
-- squad_v2
-metrics:
-- f1
-- exact
-tags:
-- question-answering
-language: en
 model-index:
 - name: DeBERTa v3 xsmall squad2
   results:
   - task:
-      name: Question Answering
       type: question-answering
+      name: Question Answering
     dataset:
       name: SQuAD2.0
       type: question-answering
     metrics:
-    - name: f1
-      type: f1
+    - type: f1
       value: 81.5
-    - name: exact
-      type: exact
+      name: f1
+    - type: exact
       value: 78.3
+      name: exact
   - task:
       type: question-answering
       name: Question Answering
@@ -54,18 +54,21 @@ model-index:
       config: squad_v2
       split: validation
     metrics:
-    - name: Exact Match
-      type: exact_match
+    - type: exact_match
       value: 78.5341
+      name: Exact Match
       verified: true
-    - name: F1
-      type: f1
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTk0ZGQ1YjU1YmQ5NTc2M2RmNjg2OGViYjcyODZkOTc1MDBkNmI5MDc0MzEyMzZmNDg3Yzc4ZTA3ZjAwM2M5ZiIsInZlcnNpb24iOjF9.ewKF-UetUoxKDeXgnM6vqy8nBC9c3qh7dLZhdQlgSxPut3LjAhpCh2fJGir-OVcfzWzxsPhcZQEpdnxR8oZnAA
+    - type: f1
       value: 81.6408
+      name: F1
       verified: true
-    - name: total
-      type: total
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTQwZDdjY2ZlOGVhM2E5NGM3OGNkNTk2NWFkYTg1Y2Q0YWFlYWJmMGIyZWM5ZjMyYTYyODUzMDA0NWU0ZGVkZCIsInZlcnNpb24iOjF9.BHJNhS1YisUIkjcpIMdwXurTewak9dkkpGXC2vHvUB4qUEuk_p3V-orhmeFyTxzLaWRwrZVGVz-NSfqFr4n1Ag
+    - type: total
       value: 11870
+      name: total
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzNiZDQ3MDAyNzljMDI4NTRlYzZiZjE4ODJhZDhmZWE2ZjcwNjg2ZWJmNjUyMTUzZDk4ODNjNDExYTk1YWNlOCIsInZlcnNpb24iOjF9.3BlfmMvbV86Ua39ToqnMmgpGS0ZTew0UFFYWGyTkS3u7jaAXCfYkFkNJXw806f2uFFkKr1hqlzzKfivV0wUjCg
   - task:
       type: question-answering
       name: Question Answering
@@ -75,14 +78,16 @@ model-index:
       config: plain_text
       split: validation
     metrics:
-    - name: Exact Match
-      type: exact_match
+    - type: exact_match
       value: 84.1741
+      name: Exact Match
       verified: true
-    - name: F1
-      type: f1
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTA0MDVlYWI5NzdiNjllM2NmZTYwYmQ5YzE0ODgwOTA3MWZjZDkxNDFmZDM1OTQzMzgwNWI4NDc5NThhM2VhZSIsInZlcnNpb24iOjF9.lc2nUBxSu2_0_a5lyVsV51UAmkE8WHDTwGHvt3n9zvCbcJ1ylOg2xovF0_j0hZS16lv1DEw5XV8EW_ZS7mfvBg
+    - type: f1
       value: 91.0771
+      name: F1
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODQxMjkxOWJlZTc2MmE5YzVmMjNhOTkwNDdiMDBhNWUwMDU3MDI1MmJiNDY4MjczYjIwM2U1NDhlYmZlZWQwMSIsInZlcnNpb24iOjF9.x_axHiBX5d3UIi1UbJT3kVbdX4kX9XFLQSg-l16-AAK9tiyutT-yaYJOi8LSb2lR4677tJpf3itu4eriJRU2Cg
 ---