Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#5)

- Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (fc78337a7faf2b3b95ce48ba2bafb332b6f98c99)


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

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: 24.5482
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2U3MGNlNzI0MGNiYWQ2NGRhYzg5M2Y3NjhjYTdhZmVlYWNmM2Y0YTFhN2I2ZmI5NDVkY2I2M2MxMjM5ZDIwOSIsInZlcnNpb24iOjF9.tHnV8ofGr9jbx0fHm3cDL6p8nqXZITS1H6XLjW-iWaNFuQJ7Qfs7E0uYNf2haQP6Mu5K5eWWGdg54KtMi1N9DA
+    - type: rouge
       value: 4.811
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzE1ODYzOGFhMDE4ZGU1OTM0OTM5NDBkNjEwODQzY2I1NzRhYTc0NDJjZmM5YzI4ZGZmZGNkZjljYmNlYTQ1YyIsInZlcnNpb24iOjF9.n7tOZFKEePwSEqM7a0Y-fBiEEi3jZL7QwP0MCQNun5yKsd2OIkTlruuauV3h8yHN5yKxg33CUfpzS2B44kGjBg
+    - type: rouge
       value: 17.2505
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjM3YTYwNjAyYzY5MmZjMzI1MmYwNzI2OWNmMzJiNzk3MTY5Y2E4ZmM1OTIyYjQ1NTkxMjI1ZGMwYmRiYzg5NiIsInZlcnNpb24iOjF9.1VQIehrugMj213RavmSAf1qsKTG3Jmj6DAJGi3KOeOYrJpKeLBQ6ftQZ_wSje8UiyR9uekne1wTd256sr61DBQ
+    - type: rouge
       value: 20.906
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDdhNjJlOTY3ZjgxOGMzYjkzOGI2NGJlZDY0MDk0NmE5ZDcyMzIyNTA1M2ZhNmMyOTFlODJjZWJkY2ZjMTQ3NCIsInZlcnNpb24iOjF9.SLAdCUY_9PFb7BrvvpN2ABDU9uvy7EIMEHKtnlpH94nZbv2G2sj74tWLcIQstuTkmXmLTk6_HvdZTEaoUc-5CA
+    - type: loss
       value: 3.3002164363861084
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
-      value: 52.0
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDFkM2UyOWQ5YzM2ZDIwZGRmNTY2YTRlMzUzY2QxZDhkNGFmODljNjIxNWQxZjFhM2E2YjM4ZWRjZDUzNWQxNyIsInZlcnNpb24iOjF9.HUYhxEAGbZS8J76Zt9k5KNFt6dx_vdoqf34k5ht3X0BTB4u2WiYwVS9O0ka2ExCynIODo9OMWLcMG2CW-xnjBA
+    - type: gen_len
+      value: 52
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTkxMWQ0ZWVlNWUxNjYwNTU3MTQzYjRhZGI1YjQ1ODYxOGRlNTU0ZjlkOGZiN2UzM2I5MjU3Y2QxODU3MTJmZCIsInZlcnNpb24iOjF9.9iDB-q3h2qYZIRHLKryZIjYYUeN_4_9hr5miRgmJl8TYB1Prf69NNziW7QPOkMXMOM-5-xvRVKmx-JqZQSkcDg
   - 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: 35.3305
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2Q0NWU1Mjc0ZTYxOGM5NjI3NTlmODYwMmU4ODE3Y2VjYjdmNTRhOWI2MDdlM2U3OTk5N2Q3YTcyYTViYzIwMiIsInZlcnNpb24iOjF9.ScFds-4QZgG0Wro-w0qnoaQSoXXMpWOTEE4zYrvA9k2lew965geaqeBVAt7QQxwchuB9q26hSGYCEqLMdX3EBw
+    - type: rouge
       value: 5.8001
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjFiNjU2ZjI1YmE2NDViZjUwMjI1ZWFiNDkyMjExZjJjMjBmN2I5ZmYyYjE0MGEzNzk3ZGE4YTMzNzA0M2NjNSIsInZlcnNpb24iOjF9.H4r1JTjEC3ABkgVIi8i3TRxQ1gMsYoQR8qCBbJVkdWJQwECzWGZRw6QIaWz0kZv73nQ890kf90JE6FKeD2MpAg
+    - type: rouge
       value: 16.0557
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjBjNTBiYmM3OWM3ZjFkN2FjZTBiMGJkMTg4MTYxYzRjNWUzNWE2YWVjOWJiMzRkZTMxMGFkYThlYmZiN2UwNSIsInZlcnNpb24iOjF9.mLij-24wue3udXSS5H3kBniefh7NDTmNf3bxacq7UinFkbTtqx9OvS6Ywun4LfJj_Ufn9-uTMR2VbaoIIQKkBA
+    - type: rouge
       value: 32.3409
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjg3ODliOTAzYzg4Y2NhNzI4M2I4OGM1ZGQwMWE5ZjBiZGQyNTNhMDQxZDllMzgxOGM0NWZjZTJjMzFkZGVkZSIsInZlcnNpb24iOjF9.LpNcyf7HNaL_xwb4zqrBgOPoTBWFaBN0AgSbzsgfsQ7J12CIi7s0UoBhxg_c8UYwNuqFOZouYIq78r1PM81RCA
+    - type: loss
       value: 3.0063540935516357
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTJmMGM2Y2U0MDU0OTFlMzJlNTNlZjViYTAyYjE4YTVkOWJhMmQxZjc3MjM4ZGNkNTNmOTViNDYwZjg0MWI0YyIsInZlcnNpb24iOjF9.VLKkHEjp4Iq1r3-CXSABBzgPJFx1sbjRt5KbbKe_AEuKuJtXI6rRWPuBjudOLB-CHBvutDzVS9wR60pGaQ5jCg
+    - type: gen_len
       value: 268.4032
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjJmYjZhOGFkMGNkZjEzOTA0Y2RjNWU3Yjc2ZGI5NWU1MTNjZjY5NzFiZjI0YjBhZjUxMDFlMjBmZTYxMWE0ZCIsInZlcnNpb24iOjF9.vnImpJVQBidfhKVOzEYuA2okKgbTvB0bkc4GNmvkTlxXdZlsqg1KuevQa587lmy0LQOZk1_pYWz0aVJ4VQQQAA
   - task:
       type: summarization
       name: Summarization
@@ -91,30 +103,36 @@ model-index:
       config: plain_text
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 37.0412
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTQ0NzdhYjdlNDNhYjJmNzQwM2E1OWQ3ZTQxMTZiY2IwNjJkMzE0YzNmMWZjZTI0NGI2NWYzNTU0ODM0OTVmMCIsInZlcnNpb24iOjF9.1Gf6zoMOLmf71bkW9RdiXJPDms-vfc0hu0jJehdb7XCjW-hPcmLxdk8ALwWi9knBmeHZ18GHHSJklgU_maFoAA
+    - type: rouge
       value: 8.519
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2M0MTE2YTE5NmE1NjhkMGM0ZjYxMzJiOTFjZGNmOTdlZWFhOTExZTAzOGUyOWE4Yjg4MTE3NDcwZTg5ZDk0MCIsInZlcnNpb24iOjF9.6EeSA2FzddyK5EfHhBViKNDXIZp9svVTpvSi4O_9YULWX6Gs4bZYcGRQATGLS6Pfvh1swky1ZXXR5GpX4tN-Ag
+    - type: rouge
       value: 17.8685
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTZmMWRhZmNmZDY5MzYzM2JhNDc5NzdiMWI3MmRlYWViZjA0NGQxZDJhNjIxZTY3ZTM2NTJjYjI0ODE5MGFlYiIsInZlcnNpb24iOjF9.Tz6vT3YFZO5Hd8BySoXmtcwDQMSvr4DLGvKYpTeH7L0iZOaIFr8XILCPbLV6ZxjglSgFwMzcwsjN1d032mEqBA
+    - type: rouge
       value: 33.5036
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzgzNGQyMTIxYWUwMDlkMjQwZDE5ZDRmYzczODJkZTIxOGE5MTEyZDNjYzMzZWFhMGUyMjljNDQ5NGQ4ZGRkOCIsInZlcnNpb24iOjF9.oR8vSpgDjMskRmcImHV4E5dkXbP74BKNYXmfpkpO5zIHIJWNNyJvUSKurDDy5rhbhbkI98kF5GmOcLlfghyrDA
+    - type: loss
       value: 3.628979444503784
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTNkY2E0Y2Q1YjA3Y2VhYTAyOGE1NmQyYWQ0YzM5NzczOTBkYThiYzNjMDljY2YzZGYzMGQ3NGQ5YzRhN2M5OCIsInZlcnNpb24iOjF9.kD1yDRyt6PR5wKBHvsU4l6stGmcsvPbkGB1dMgSfvMWV0LjjSc3MaXUS2ykNciLdnJK_aSqIjSUbUDyO0e4oDA
+    - type: gen_len
       value: 219.3885
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzI2MjIyZWViY2I0NTE0YWMxYTE3OTAyODdhOTNlZDZkOTIyMjQ1NzdkMmU5YTY5NmNjYTNkOGI0ODk4YzE2OSIsInZlcnNpb24iOjF9.sqlm-kWBzo-sJ4PaelnJWeQ1usF3nM5ZJP8igXE2GhWNhAQVsST3tlvcA8GwRtfbVCAy_x7Ex9iOuYqpccdbDA
 ---
 
 # long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP15