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 (29c3c2e2c141393d7d2fb5d02982280946480fbc)


Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>

README.md

@@ -1,13 +1,13 @@
 ---
+license:
+- apache-2.0
+- bsd-3-clause
 tags:
 - summarization
 - summary
 - booksum
 - long-document
 - long-form
-license:
-- apache-2.0
-- bsd-3-clause
 datasets:
 - kmfoda/booksum
 metrics:
@@ -25,30 +25,36 @@ model-index:
       config: samsum
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 23.5177
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjMxNGRmYjc0ZjNmZWY3YjFjNDEzYjRhYTAyNWNkOGQ3ODMzM2EwMzk0NTVkMzQ5MGMyYjYxMTkzYWQyMjZiMyIsInZlcnNpb24iOjF9.-PPUZc4Jr6EjNcQ-u9n814SfeviFEaddbFco5d1wbJNoECN_HqciNphSjXh7w99I_rQ6rPIXu8DA93u7aFj9CA
+    - type: rouge
       value: 4.668
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWMwYWI1NTg0ZTUwNGIwZjlhYWU2MzQwN2I0NzA1M2MyOTA5YjQ4MTEyYzU2MjRmZTA0NzNiYWM2ZDU0ZThhYyIsInZlcnNpb24iOjF9.CQfgJ3Lha9XR2-IudjfFuaUh_uphWPdYk6TMQOLriWM78_X-paqEIBZDh1Q-WbWoUf-CAyf6UvqXqELRDb3hBQ
+    - type: rouge
       value: 16.6091
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzhkODRjM2FiYTFhN2E5MWFiNzk3MjgzMGI0NmY0ODNkYjAxZWNmYmFmYmY0NDBmNjRmOTBkMGVhMGYzMmRkMCIsInZlcnNpb24iOjF9.Y66qsqvvGeAoiMCr1xa9enBMfcXt6a6I2i5s7VAJ3aoh3DtM2RlaMm4nuXG4uzWHedWW1NDivBWMZtycYed9DA
+    - type: rouge
       value: 20.3174
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWJjODE5NDdlMjM2YjNkOWU3NDJiMWFlZGU2YTRkNzliMTg5MGNkNDQ3YWU3MTBmY2E5ZTUxMzEyMDc0ZTU5YiIsInZlcnNpb24iOjF9.Kc1accwOycbNU1F7AT8LV8jC3NpYKMmOsZmdLeDdIi5BqgMJcQSP8oNt3L-hGbscLb-D7iIvQBFtmmiGqpnGDQ
+    - type: loss
       value: 3.2174887657165527
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTQ0MzQxYTQ1M2NiODcwNTBjOTRiMGEzZDE0NDFlZWJlNmNlOWI1M2M1N2Q2ZTVkNWFiMzQxNDhjODQxNDFkYSIsInZlcnNpb24iOjF9.Vat1Thj2t_1of477BCINeYoTeNZX1NIPG13qVskJ44ivKLJgMr4BCp0luYNEi2skNTv3kYK2orqBdDfxPZlfDw
+    - type: gen_len
       value: 57.1966
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2I3MmZkMDY1YmM5N2VmMGE5OWQ0NDg5OWM0OWViMzU1ZTM1NjBmYWRmN2I2YmM5YTVkNGVlZGViNWEwOGYwMyIsInZlcnNpb24iOjF9.4c6j-ll2veK_PuCcXvRK8-8cPFdedKsqGHQsEhGpwj48uwI3PMqj9mF4HYvSGq5H3rVM_dvyPEEs9RhjCvSHBw
   - task:
       type: summarization
       name: Summarization
@@ -58,30 +64,36 @@ model-index:
       config: kmfoda--booksum
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 35.9884
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWMzODFmZGYwZmNjY2FkZTJmZWYyMjI1NDdlZDI3OTdmY2MzNzU0M2FhYmMxNTdkOGRiNzIwMTEyMTMwMTgyMSIsInZlcnNpb24iOjF9.pbT1OOzVOjnUp4q6lcpUPunDYTQqOiwQeRLRV69699SoMI3ay4bfd_hbWZUvXOuivoJ5JiDd9KBhEqYUninNCA
+    - type: rouge
       value: 6.0596
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODNkNTE1NjU5ZmY3MmVmOGQxMjhhODRhZjIzMDRhMzJlYTY3YTkyNzM4YTAyMGI2YzRlMzljMDM5YzFjNzIyOCIsInZlcnNpb24iOjF9.NevkOank_Ou1u2ZfkEa3o4FF4DapvpFK_ucxLRm-xL-ZWGl9cLdLTOxVECrTn8Yasi_sWrjZUhGRWPkCKlJADQ
+    - type: rouge
       value: 16.1419
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzNkM2M4YjQxM2IwNzIzMjAyMjM3MThlMGQwMDgzMGI3NDU0NWVlOTFhMzBlOGQ3ZTQzOGNkNmE5ZGI5NTkzOCIsInZlcnNpb24iOjF9.8DYhyJAiKIK2aIkQSwMy4NEiBSC4v8_h_3feA-TFBdd-icGg5YvKMQR7_IOa1-9AHBe6PphVSFjl82-nDp6lDA
+    - type: rouge
       value: 32.9992
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTEwMmViZmZjMzA3OWYxNWMxZjFhMDBmMDRjOGViYzdiYzllNzk0YWZmNTU0NWIwMmVmZjQzNjlkZTBmZTU0YyIsInZlcnNpb24iOjF9.KFwuSVaUXx958EWZctKpK1wawA0EH4yxBJdp3Zru4Sn97oSyP_s5m-jjZiLfP6kmSajd3849dna-Uw77s3sVBg
+    - type: loss
       value: 2.9468588829040527
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzhmODMwMDM2ZDFmNTMzZmFjMmJjMGQ0MmQzMDcyMmFiNmFjMzBhY2RjMTI1MDhiMjI4NTEyYWFlYTNlMzE0ZSIsInZlcnNpb24iOjF9.PHX9VAAgiUGOR8Uxuam4otU65hIzW6hBapaf1KY8o1FDfaoHWAKbSnpjZ3nXKYYeVV6LyGRny_7RdRbbbM8LAA
+    - type: gen_len
       value: 298.2593
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGYzMDAzNTQyMzgxM2RhNjY3MDIyNGEyMWZjYmYyYmJlNWM3MTFkYzRjMDhkMmZhNDZiN2FhYTY3MGI2NDcxNyIsInZlcnNpb24iOjF9.ax3H6LohHUodVGhSMUWMZZZ-bCTXHEaGpK4jXuOdZkGsewYrX8fO1oRA0uDjACM-eceKFfVnMveHoU9EdMaeCA
 ---