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 (eadd643d7cc28487c12c70b223699f816a436006)


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

README.md

@@ -15,30 +15,36 @@ model-index:
       config: default
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 38.643
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2E1MTczZDhmODNjNjY2NzU5ZTJlYjM0ZWQ4YmUzN2NhYTExOGYxZTU5YmU5YThjM2FiZmVhMzU5OGE2NGZhNSIsInZlcnNpb24iOjF9.jdp1DkzoLLLpNknLrIC8oxcOKt0si9iK7r3qMuh2UVzSeHr8aG3kMNjpybMw3C9hhb2ebXzUpWok2ILvRSZTBw
+    - type: rouge
       value: 17.7546
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDViMTgzYTQxNzFkZTg0NWY2MjgyNGQ0MmVhMDBkMjMyMTllZWM0YzE5ZjQyMmEwY2QxYTViMWMzMDQwNzdiNiIsInZlcnNpb24iOjF9.ja641EZwDrll0akyPOATo9Rqj1uaCpAftziHd0mi5ZuLqCUZsh8H0OLfjvZLNK1JwtkMi3n_P_8UYvmG1tuiAQ
+    - type: rouge
       value: 32.2114
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWZhN2YxZTI5NGQ1MzRiYTEzZmI4YTRmYzY5NTMxYWVjZTRhODFjZTJlN2VkZWRkNzllOTE5ZTA5OTY2OGNiYiIsInZlcnNpb24iOjF9.hs2yl3ArmJuDo_N87MUWqcJ034sCjD8borR4kE_D91z0aL3NilFdpDk2iuyynE9pCn4JttetiGRLngpMvKekDw
+    - type: rouge
       value: 32.2207
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWJkMTdmYmJlMGY3ZDg0ZGU4NTk3ZDRiMTg2ODUxZjU3ODJiMGNmZGZiOGFmNDhhZmRkMTE5MTM1YTMwNDI3NiIsInZlcnNpb24iOjF9.nTXRauPJTCmm1Ed4mp4LyIaWKd0OXhK94OAZEnIpN549pMZ19ufrNTuBeXQj6vLQAsaugbrPotBXBPe-Pbp3Dg
+    - type: loss
       value: 1.8224396705627441
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDlhYTY5MzFkOGRlNGFjOGZiYzUyYmQ3ZWViNmY2ODZiYzhjNzYyYWZlN2ViZTJiZWEyMDFlYjE0YmIyODY2YyIsInZlcnNpb24iOjF9.96OPA94rxBtQpSiEEk7hBffOa30pe1TslYE9cpZiiwQb7GOCNGeUqjxWmzE0-R1_QluMN527k0dFL1G2KWQwAA
+    - type: gen_len
       value: 19.7028
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzU1Njc2YmYxZGM4NjA3ZTMxZmY2YjBmNjhiZmE5YzA5Y2U2NDNjZDM0MWNjZjAwYjYxZWVmNDZjMDc5MGM2YyIsInZlcnNpb24iOjF9.j7cYnDB8LQ_stl35EaHKKJhqavj9mHVroOkzuk88rV8eRWhpksKg-n1FfbXERhxKIUBrQIWszyMUlEvAV5beBQ
   - task:
       type: summarization
       name: Summarization
@@ -48,35 +54,36 @@ model-index:
       config: default
       split: validation
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 38.7415
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjdhZTc4MGUyODM3ZDBjNmVhODRlNDMzNWJmYmNlM2NmZTEwNzc3ZDYwYjllMzc4ZWE4N2FlNWQwNDhjNGZlMiIsInZlcnNpb24iOjF9.a3dZeqsFupDVZOoSrw3FRC7ysZ04930QQKNLLyJkmoSbh6p9J1IVa5Xih3RTmQbYAN2XczTSbpQS7RqpOGE3Dg
+    - type: rouge
       value: 17.8295
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTRmN2ZjMDM3NDgwYzVlODcwNmYwZjVlODcxMGE4ZDU5MDQ2ZDdjMjEzZWE2NmNiYzRiZGZmMzkzN2EzZThlYSIsInZlcnNpb24iOjF9.3E8u6Ia8_ri_qcNjshPFEPEyED3cK1dNJr027fdjn0_DjY7PDsnP6pmeNv4YJJSTWTX_itiX69zcdWK5m4WPCQ
+    - type: rouge
       value: 32.2861
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzllOGNkYWI4MTdiZDc4MjgxZGUzNWZlYzkyNjlhNTQ3Y2JlMmE0NGZiNGRlMGMxNDkxZWViNjk2OTFmNmJiYyIsInZlcnNpb24iOjF9.cqrqGe65cej66-c3JjQebMx3kiM1nGOVMpN0ZbqnCRFoMdqqCIVG3ZjP-LJY3MptXRqk_sWY_O5kMximu5sgCg
+    - type: rouge
       value: 32.2763
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGNkZWQzMzcwY2YyYjE3OWM1ZmJiMTExYmViNTU2NjExZDdmMTQ4OGZkOGZiYjk1OWQ0YTY5YjU5NTI0YjQwNiIsInZlcnNpb24iOjF9.pLFILxKJ33wPSDByZz-IQv_ujRzypMeblgc3C7_3eO5egte0_hTnjl4u-m8KLGYy7mfVXFHZPpvihwlShrARDg
+    - type: loss
       value: 1.8132821321487427
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmRhM2UxMWRhNjk0NmIxODQyNjEyNmEwMzYyYTc3NGZlN2RlNWYyZjE1M2NlNDQyOTM1ZGU2MDQ1OWY1OTYyYyIsInZlcnNpb24iOjF9.ZTCMjc6AwjXjO7mHiVPCSyYX1eAPX5IDbWSckWIQpH7O9qk8Sm4WXST-q26Mtf4WOkn2u26Lf171ATBH5GyCCg
+    - type: gen_len
       value: 19.7116
+      name: gen_len
       verified: true
-  dataset:
-    type:
-      xsum: null
-    name:
-      xsum: null
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2JjMzcxZTI0MDQ4ZDk3YTVhYTZjYmRiYmM5MWUwNDM0MjFkOWZiYTNlMWQ1NzA3MDMyNTI5MjY4OGY5ZGYwYiIsInZlcnNpb24iOjF9.JJ41buqEz-r4GSHAAB31_gofuzjEm0fgui9ovJJbJZLTcooGHAbYMBuDAZM8ojwFEu6S2VTR0fJE60OCs278Cg
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You