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: adversarialQA
       split: validation
     metrics:
-    - name: Exact Match
-      type: exact_match
+    - type: exact_match
       value: 42.9
+      name: Exact Match
       verified: true
-    - name: F1
-      type: f1
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODRhNDM3Y2RlYzgyMzQ3MDdlMzc1YmFmNjFkYjYzODFiNjU4Mzg5YmZkMTI0N2U5NTAyMTA2ODQ4MmY5Mzc3MiIsInZlcnNpb24iOjF9.jFyNzcBNLdKPZJHtcwmSE_rgT9nT1EavaleEGtB1U9fA2iGkjUFeWcF539mNrUSzfObj5tCbNWgHGASa7gPQDA
+    - type: f1
       value: 53.8954
+      name: F1
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDQ3MzhmMTcxYmM0ZjA2MjgwNjJkYTU5NDkyMGNiZjZiMDc2MzZhOTM2ZWM3ZDIwMjg0ODlmNGZkNWU3ODkyNyIsInZlcnNpb24iOjF9.8eXunF16sRKtW0tfSBMFjKA2LUVPzgIxkjQ1d2qz0FyEYA7PM0Zp5DJ_WhlIowbvjKAe5YQOV-ACCksS-_43Bw
   - task:
       type: question-answering
       name: Question Answering
@@ -36,14 +38,16 @@ model-index:
       config: squad_v2
       split: validation
     metrics:
-    - name: Exact Match
-      type: exact_match
+    - type: exact_match
       value: 79.5382
+      name: Exact Match
       verified: true
-    - name: F1
-      type: f1
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmI4M2I4MDJiMWYzNjE0YmU2OGNmZjU5ZDA5MzM4ODhlZjNkMjMyOTQ4YTlkYzdjMGYzN2U5N2IyOGQwM2QzMCIsInZlcnNpb24iOjF9.vQ0xbOhNvzMXefT2VKpDdCzIFj80KxFD3fVk_qNaPH9TzHw5Vu1rBx6GVePsYblSV7-VwR20WMuKsitRNRrMAA
+    - type: f1
       value: 82.7221
+      name: F1
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjBiN2I3YzE5OTQwZTg4NDE4MjBiODY1ZDQwMzYwNmY0MTA5NzJlNTg0NmEyNDJkZjRhM2IyZWM3MDQ3NGU3OSIsInZlcnNpb24iOjF9.QMaxPxW1SU-240Qx_aNr6BWTJ67nEy_abhgTmrIk4PreH5EbH13H8Kn3u21p85XmDNMPBxE-uh2mR57x1bjJAg
   - task:
       type: question-answering
       name: Question Answering
@@ -53,14 +57,16 @@ model-index:
       config: default
       split: validation
     metrics:
-    - name: Exact Match
-      type: exact_match
+    - type: exact_match
       value: 78.403
+      name: Exact Match
       verified: true
-    - name: F1
-      type: f1
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTY1NzA2NWQ2YTgxOWNjNGM5MTc5ODVmMjI5NGIxZjZlOGQxYzUzNDI0YzgyNjdiYjhjMDc0NmY5YTZkZjg4YiIsInZlcnNpb24iOjF9.PyLmsoXlKaTryvr1L7SGp9tBMyKwe9YDodYjXBw1sA2F-AHts_G9RPljx0ujFYbp7mcVuTKkzeQ3mGHZpG0eCw
+    - type: f1
       value: 82.1408
+      name: F1
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjE2MzY5NzFhYWVhMzJmNWYyOWQzYjJjNjk5OWNkZWMwODNiNmIwMmQwMzcwYmEwZjBjNGZhYmI2OGNkMTk0YSIsInZlcnNpb24iOjF9.9dRYfF2mLRsUCD5uTE9h1vfSSMFzDmjVkFEAjl0h1BSaNUCxLk6aDMeYin3qi7kG4SEeqrRycg_Cc0gGUQmmDg
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You