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

README.md

@@ -14,14 +14,16 @@ model-index:
       config: squad_v2
       split: validation
     metrics:
-    - name: Exact Match
-      type: exact_match
+    - type: exact_match
       value: 79.3917
+      name: Exact Match
       verified: true
-    - name: F1
-      type: f1
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTFiMWI5YzFlMDZhMzc2NDIwYjNiZmIyMThmOWQxYjFjZmM2ZDQ0OGM2NmNlNmI3Y2U2N2JjMmVkZTgyZjNiOCIsInZlcnNpb24iOjF9.MCw9UJ3MI3Lf5hvOgk7Lw2xZfN4678p7ebG3vnGXX_Avw6fELTPwxZ9qGA-9tL00p4NxaSb3Cx6XAFvWetAIBA
+    - type: f1
       value: 82.6738
+      name: F1
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjdiYWY2MzU4YjZhMWQzZGJhZTk3NzU3Y2UwYmQ4MzliZmQxOGUxZDllN2Y0ZmZhYjVlNTE0MzY1MjU5OWMwMCIsInZlcnNpb24iOjF9.zeWLwXy77n0YKxGA5gjySe8p-_nPQxbiPnvQU2tF45IyMmlYKUuLeq4hJnNe-5NgriTf8xkBJBE7Cr5lWHy_Cw
   - task:
       type: question-answering
       name: Question Answering
@@ -31,14 +33,16 @@ model-index:
       config: plain_text
       split: validation
     metrics:
-    - name: Exact Match
-      type: exact_match
+    - type: exact_match
       value: 84.9246
+      name: Exact Match
       verified: true
-    - name: F1
-      type: f1
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGJhYmU0Y2I4Y2UyOGVlOTlkMmQ2OTcyMTZkNTkwNTMzNzhmNzZiYjU4ZDkxMGM5NzAyMjk1M2ExNGIzOWU4NCIsInZlcnNpb24iOjF9.ql1rCId6lQ7Uwq2spG3q2fFppkFGHA1IWQjvyPRhvKdRNzApBO0mu9JjMAv4uNKZX-kmGEkI018_9tAzN7kwDw
+    - type: f1
       value: 91.6201
+      name: F1
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjBjMmI0OTFmODVjMzllZDM0NTdmNjU4NGI4NzA4NTJhOWVkMDQ5OTY0MDcyMWEwZTFkODNlY2VhZjU2NWJmZSIsInZlcnNpb24iOjF9.rGvF60bfWIXzB66C7fkdxCtZvRZ_m3onbLaNbs7M4M0Fk27xnMat6IAy1DeTztkOKLoiD2s2NQH6wXid83cgCw
 ---
 
 # Deberta-v3-xsmall-squad2