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 (fc22477eb0419b15c5ed109270c594cbc4e74035)


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

README.md

@@ -16,30 +16,36 @@ model-index:
       config: default
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 22.7044
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzMyZDQwNWY4M2I2YTM2ZjY1MWFhMWQ4NDAxNTg4N2Y2MDE4NGMyMjJiMTkyYzcwNzg2MWU0Y2YyNGU5MDM4OCIsInZlcnNpb24iOjF9.2MQgk8ReWfDWi98sJyIuEqSXUxumfMjUZl1raOfHiK4TP45FwLKzc5Un-dLbS7yb8L6rEGEKJMGbiFKeapzJBw
+    - type: rouge
       value: 5.616
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWIxYTFmNGUzMjMwODA4NTlkZjk4MTllYmVmOGJlYTI3NzA3MTQzY2RkMWJlOTdiM2ZkZWVkNDk0ZjhlMzQxNSIsInZlcnNpb24iOjF9.XwtjOwmYE-NxbH6kOYxDgMpXTNL6XwiSGGi4cdtBu7O0cdjNUh0dnfihvEvJegMM8cnQaQeu47g0zxuLP1LQBQ
+    - type: rouge
       value: 18.0111
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzYzNGExYTc5MmZiMTNhYjM1ZDhjZDNiYTNlMDZhMzdiMjRhNzk2NWI1ZjRkMDlmMGUwOGMxYzhiYzE0MmFhOSIsInZlcnNpb24iOjF9.nPERc8JZ4VaUTSkUZS7vwbZecdWn1uIpIBN6zFTFLQnfuCIP7ZlgDegUGEaehoERJubHVf60Z24I0aYxq2q0DQ
+    - type: rouge
       value: 18.1554
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjMwNTg3MWIxZGQxMzdhMGM0NTg5NDZlYWZhZThjYTUzZjcwODUyMDgwNTY0YWRlOTI4Y2NlOTY3Mzc2ZjU2MCIsInZlcnNpb24iOjF9.syWVW4_SlY4JDqE96kpz3qGXGfhF8wezAj87p4RzQpJ7Fp7ie1-v5EgTOy4ZFMdtemQCyqiQYAQwcVckttrLBg
+    - type: loss
       value: 2.1656227111816406
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2UyNWMwNmQwOWU4YjA3MzMzYWQzMTgwYzJjMjNkYTlhMmQ4NTAzMzE1YzlkMWRiZDEzYzJlMGJmMzJkZjEwMyIsInZlcnNpb24iOjF9.8FY9EcQPrS4KXJyJBuX2uLD5VxLlGxRC33qxPuyAg5W9WsXm6XSjb0ZCJ8T-Xl3YlwV9bSL6UMq4MPleEjiNCA
+    - type: gen_len
       value: 18.3527
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2U0Y2E5NzU1MTNhOGRkYmNhNjI2NGQ1NjJiMDc1MmI5NTE2MDJjMDA4NjMxODcyMDJhN2FhZWI0ZThhNzZhNyIsInZlcnNpb24iOjF9.e3yQ--2AjvVzCM-HXzvB-lN4g6eMxqjQ1AyhFqftit8kFmoKnLqoa2ytoyOZmlnXvkCRmpgfSAYq-tnceINLDw
   - task:
       type: summarization
       name: Summarization
@@ -49,30 +55,36 @@ model-index:
       config: 3.0.0
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 21.1522
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTkwZWEzYzEyMjdjZTA5MjBlOTM5MDI3NWEzZWJkOWEwNjIwMGNkNjU4NGM1YjVhZjIxNjI2NzJkM2NhZjc4MCIsInZlcnNpb24iOjF9.f9REqBITFW-Y1GjOmq-e1zUI0qK2MQxEsCe9NQZbCFNeygvdhD2CkTslUbTIXpuDcA_bWAJsNiL2VAMSL1ZDAw
+    - type: rouge
       value: 8.1315
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjg3MDYxMjVmNGIzYzlmMTBkNjcxODA1MDliNjBlY2I5ODQ4YzQwY2RmMDBlYmYwMTgyOThlMjQ0NjY2MDdhNSIsInZlcnNpb24iOjF9.mJwLahXr-lvwEv1L9PlFfV0dqxN8m3OciTV9wdoENBaj7JLtBnev-LL8oivi-fBRY-WcVpUGpjyx1fQxwLF2Aw
+    - type: rouge
       value: 16.6625
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmUyOTc0MWVmYTQwY2ViMDNjYWE2Mzc3OWFkNGI1YzUxMmU3YjgxMjMyMmY5ZjIzOGRjYmY0OGIxZTMzN2I5MSIsInZlcnNpb24iOjF9.1gGyxK6SIY4AcR_6-7An94GyRx4q_Fj4Zmm8zNSE4HqHq3dFUmWfFYGZVgLUOswMr03di63QqmFyVnjW0TqmBw
+    - type: rouge
       value: 19.3603
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGRmMzkxYzRkMTA4ZDYzZWE2MDM4NWU1NjFiYWVjOGVhMjc1N2YzZWI2MmY2OTY3MjVkYmExZGY1ZTcyYjIwOCIsInZlcnNpb24iOjF9.vVMF4qaE5Wg9vZuBVOtcR89L_NldNk49sgEyAFVvx_hhjOx5nZvygseHcwqemMjUlrTzOuRD15x-XbH-62qhBw
+    - type: loss
       value: 1.899269700050354
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTU5ZDUzYTc0OTc1YWUyNjY0NDU3NDhlODljNGNlN2E4ZTQzYjNhMWM0NDYyNTE5Yjk4ZDE3ZTNjZDdmYmQyYSIsInZlcnNpb24iOjF9.SuRSjdfuA_NE3WHglrxbIaPZ-Hg9-F6jB37Cb_MPIME2h3a30qafO9tFmxUsR_JCDNfuILwrGEHT1PJmq4NQDQ
+    - type: gen_len
       value: 17.853
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWU2MDRmMTliNzhkMzdmNmM2NTA2Y2NmYjVhOWJjYmQzZTUxYWM1MGYzMzBjODdiMzY2YjMzYjE4Y2FkNjExZCIsInZlcnNpb24iOjF9.J5NYms5Hg9iLFgTq0YqYXP86H9A0PClmG2eLi09BBs9L8F-PhQhiuzzCeD1HA2fC_6mtLyEv6PPLZCr6Ax7DCQ
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You