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

README.md

@@ -19,14 +19,16 @@ model-index:
       config: squad_v2
       split: validation
     metrics:
-    - name: Exact Match
-      type: exact_match
+    - type: exact_match
       value: 79.2365
+      name: Exact Match
       verified: true
-    - name: F1
-      type: f1
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmUxNmNjZTg2YzcxMTBkYjE4YTVmODM3YWY2NTFkMmY3NWNiMGYyZTkxZDlkMTJiMjBkZjVhY2NlMGRjYzAyMCIsInZlcnNpb24iOjF9.dn0e2EJ8ImOWODCoRH_d7v10vtxv2ZfRkeWKF-R62sz2ufMjyC9brQihULMw5ZhnSQq5bBFFvauhG6KpLgzgDA
+    - type: f1
       value: 82.3326
+      name: F1
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWQyZGNhY2Y3OWE5MTg0ZDM4MmQ0NDk5MjRmODA2OTVmY2ExYTc1MjM2ZTcyNzUxMGI2OWIwMzY5NzMzNzU3NyIsInZlcnNpb24iOjF9.j2Y2sfHayDV5Qfka1bVSbkBIAyMa-rpUxMNICTFvsDVTCnzRPkNVrtrE9dBiDKQa2vVOZNiKrbJEDfXE1xOIBQ
   - task:
       type: question-answering
       name: Question Answering
@@ -36,14 +38,16 @@ model-index:
       config: adversarialQA
       split: test
     metrics:
-    - name: Exact Match
-      type: exact_match
+    - type: exact_match
       value: 12.4
+      name: Exact Match
       verified: true
-    - name: F1
-      type: f1
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDExM2Q2NjIxODU4N2FiOWY3NjVjZjNmNzYwYWNhODllMzQxZGVkMzZlMWUzMzJhYTQwMDZhMGQyZjZjNWMyNiIsInZlcnNpb24iOjF9.rMzb2Cna0y3MljrLCRZ8r8SwPFTtwr4OG1mD6gdn3zcVgqX3Td0Q04n_O7RoGuH1788xqEvdeGltd-_TRrC0Aw
+    - type: f1
       value: 12.4
+      name: F1
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTNlYjgzMzZlNmYzNjkyYjg4MzYxNTZjZjNkYzA0NTZmNjk5MjI5YzM5YWQ0Y2VlMjVkYWIxNTk2YWJkMTQzYyIsInZlcnNpb24iOjF9.Du89uCtL2-mlV-tewIVKqwG9O53JE3B4Jflpzv4nptpa0MtYiGUAMCunMuWRdBXMe_YdqKDjr7_alJ0-XNRVDQ
   - task:
       type: question-answering
       name: Question Answering
@@ -53,14 +57,16 @@ model-index:
       config: adversarialQA
       split: validation
     metrics:
-    - name: Exact Match
-      type: exact_match
+    - type: exact_match
       value: 42.3667
+      name: Exact Match
       verified: true
-    - name: F1
-      type: f1
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmJmYmU5OGFmNjBjNzM1YmRhNDViNDI3MTMwZjg2N2EwYmM2ZDkyZmI4MmY5OGE4NmU5YTA1NThjZDdkYjkyYyIsInZlcnNpb24iOjF9.Iah8AxkCHsDHRTK8SLXzo4qd0C3Ku7bqGVJIJHiPxC2VO3bfz6c5emSSVZk5fACbKYMFoKTeLr6_XTwfTNjGAg
+    - type: f1
       value: 53.3255
+      name: F1
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmVlMGFiNjhhOWVjZWUzZTkwOWYzNWQzNjVhNzFhMjRkOGRmNmYwNWIyN2VmZWQ0MDZlNzk0NWM5MzgxMzdhYyIsInZlcnNpb24iOjF9._lW0JTSbvQ-pUBG0cZwpKzCvXMXmjcLrAaxk-bhou_Hf5R3Sw4AEAEy0Vx5qvxk3e30E73mYTInrtBqH8JA3BQ
   - task:
       type: question-answering
       name: Question Answering
@@ -70,14 +76,16 @@ model-index:
       config: plain_text
       split: validation
     metrics:
-    - name: Exact Match
-      type: exact_match
+    - type: exact_match
       value: 86.1925
+      name: Exact Match
       verified: true
-    - name: F1
-      type: f1
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWMxYmE4MWRjZDRlMWY3NWMxMjI0YTI5MmVkZTI5OGZiNzM2ZWMyNzlhOGRlNjMzZTBmYWM2OGU0MWM1NDc0MiIsInZlcnNpb24iOjF9.3h6zsLHiqX9ScqvvKhirv4n3S2bP1qpAmnGQrz2eoY0vps2UAN4afyXA_PLMlbk_osgN8Wvnefx74VIgELh6DQ
+    - type: f1
       value: 92.4306
+      name: F1
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTVhMWIzYWJhMWNkNzg5NDNlZTdmY2UwNDM3ZWIzZmZjNTA5NDNiMjk2NjI0MTVmNDRjOTYyYjU0YWNmYWE4ZSIsInZlcnNpb24iOjF9.pMkm1BJU1PAsWruRIWhNFrF4DD-nXaE5Gq6sR5mZfQUoeESNWiYGU2GppAvnIEVah0PmdRQHd-DBRK0hDJ2PBg
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You