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

README.md

@@ -1,46 +1,68 @@
 ---
 language: en
+license: apache-2.0
 tags:
 - bart
 - seq2seq
 - summarization
-license: apache-2.0
 datasets:
 - samsum
 widget:
-- text: "Hannah: Hey, do you have Betty's number?\nAmanda: Lemme check\nAmanda: Sorry,\
-    \ can't find it.\nAmanda: Ask Larry\nAmanda: He called her last time we were at\
-    \ the park together\nHannah: I don't know him well\nAmanda: Don't be shy, he's\
-    \ very nice\nHannah: If you say so..\nHannah: I'd rather you texted him\nAmanda:\
-    \ Just text him \U0001F642\nHannah: Urgh.. Alright\nHannah: Bye\nAmanda: Bye bye\n"
+- text: 'Hannah: Hey, do you have Betty''s number?
+
+    Amanda: Lemme check
+
+    Amanda: Sorry, can''t find it.
+
+    Amanda: Ask Larry
+
+    Amanda: He called her last time we were at the park together
+
+    Hannah: I don''t know him well
+
+    Amanda: Don''t be shy, he''s very nice
+
+    Hannah: If you say so..
+
+    Hannah: I''d rather you texted him
+
+    Amanda: Just text him 🙂
+
+    Hannah: Urgh.. Alright
+
+    Hannah: Bye
+
+    Amanda: Bye bye
+
+    '
 model-index:
 - name: bart-large-xsum-samsum
   results:
   - task:
-      name: Abstractive Text Summarization
       type: abstractive-text-summarization
+      name: Abstractive Text Summarization
     dataset:
       name: 'SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization'
       type: samsum
     metrics:
-    - name: Validation ROUGE-1
-      type: rouge-1
+    - type: rouge-1
       value: 54.3921
-    - name: Validation ROUGE-2
-      type: rouge-2
+      name: Validation ROUGE-1
+    - type: rouge-2
       value: 29.8078
-    - name: Validation ROUGE-L
-      type: rouge-l
+      name: Validation ROUGE-2
+    - type: rouge-l
       value: 45.1543
-    - name: Test ROUGE-1
-      type: rouge-1
+      name: Validation ROUGE-L
+    - type: rouge-1
       value: 53.3059
-    - name: Test ROUGE-2
-      type: rouge-2
+      name: Test ROUGE-1
+    - type: rouge-2
       value: 28.355
-    - name: Test ROUGE-L
-      type: rouge-l
+      name: Test ROUGE-2
+    - type: rouge-l
       value: 44.0953
+      name: Test ROUGE-L
   - task:
       type: summarization
       name: Summarization
@@ -50,30 +72,36 @@ model-index:
       config: samsum
       split: train
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 46.2492
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjFlZjk0MTQxMDk5ODVlNzA4MjYyNjJiMzlkOGI5MjU0MzM1ZDgxMWFlY2YyODk1Y2QxNDk2ZGZkMmU0YmYyNyIsInZlcnNpb24iOjF9.-ZraFEyEy1BY0h3frazROc1W6DmPtkb0Rvvs_A7KeWUQQlwd4felknl2dLGS3N6K-SZ89yGd6V9QJhAGeUCNDg
+    - type: rouge
       value: 21.346
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODhjYjUzMGIzNTBmNzg3NGIwNzliYmUwZjM3ZTdlNjMyYzg4MjU5NDE1NjUwM2Q1MGQ0N2NiZWFkOGUwN2ExMCIsInZlcnNpb24iOjF9.SsmyHQ3u9ATihMR3lyNPGaB6bpe5xLG0pDeWJRyXtda4KUefVE3B2SpvluGTjOcF7ikKHPwNMs65IcRh9PTuDg
+    - type: rouge
       value: 37.2787
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2VhNDllNGI1ODQ2OGM1MWFmOGMwY2JhOTc0NzYxMWI4N2VhM2JkZGY3OGNhMTU2YmQ0MmMzMTk4NWM4NWJmYSIsInZlcnNpb24iOjF9.vLIlnNYOv8ObzVma5-tXPhKgB0ClcSBzRzn2qKep_YWMYkWCLk-AbPZKLTimmuJvzfv7naVXLtJomZlVAzQ_Ag
+    - type: rouge
       value: 42.1317
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTRiNTEzZTFjYTljZmY4N2VhYWQ1MDNhNGViZDg3OTVhOTg5NDFlMmY1NzNmNWMwNTk3MTEwODY5NjQwYjVlMSIsInZlcnNpb24iOjF9.25YRNHi8K1JXnSUwmNs0VNcsFmjhFTMK9_FglOWYcs-_UeW44SURYyQlvdTSYJl0f4fBdf6TYe2nTEWJH0_oBA
+    - type: loss
       value: 1.6859958171844482
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjlkMDQ0NjYyMjBiYTVmMmUzMDQ4NzZmMjczZTdhNzY4NWI5Mzk0ZTc2NTM4NjE2ZjAzMDI4MWJkYTUyYjVjMyIsInZlcnNpb24iOjF9.ks0DwFnTsSu05CEJ6Wlm-41yVFyWdXzzAJlURdxjExPziPCWGXGEMVdZ07Nc4ANsKjlUD508Qyb3c_a-fIjEBA
+    - type: gen_len
       value: 23.7103
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDg3YTNhNWJkZDZmN2Q2ZmY4MjhmZjNjYWViNDY5ODZiNTVhNjY1NTk2YzI1NjQ4ZDFjYzZkZDYxZmMwMGU5MCIsInZlcnNpb24iOjF9._unExkTq29yj3ZBx1XzLs38T-k294vGaq5bsTnpPDTx3mR6h1JN-hBepuRJUBdIr5jIsTsPfsMh_xlrQ3JzuAA
 ---
 ## `bart-large-xsum-samsum`
 This model was obtained by fine-tuning `facebook/bart-large-xsum` on [Samsum](https://huggingface.co/datasets/samsum) dataset.