Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#4)

- Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (7be13b96d5f8da947319fe736a45f4fa54f7f34f)


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

README.md

@@ -1,11 +1,11 @@
 ---
 language:
 - en
+license: mit
 tags:
 - summarization
 - t5-large-summarization
 - pipeline:summarization
-license: mit
 thumbnail: https://huggingface.co/front/thumbnails/facebook.png
 model-index:
 - name: sysresearch101/t5-large-finetuned-xsum-cnn"
@@ -19,30 +19,36 @@ model-index:
       config: 3.0.0
       split: train
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: <TODO>
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzI1MjFiNzJiYjVjNGMxNDM1MTU2YWU2MzIyMThhYjdkYmU5YTM4Yzk5OWYzYTcyZDQwNDg1NmIyYzNkZjFjMiIsInZlcnNpb24iOjF9.fVKnv7zkhNG6zLLpok10xyIHyYaGqiOShLXu9aDJvJNyZdKL82WHj_eP6Huv3hb5fmzlW8ZBJ_f7KOb98JjpDg
+    - type: rouge
       value: <TODO>
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzMwOTllNmQ0MTMzNzI3MjMyMjVlZTU0YWI1OGYyNWY4ZWEyMGJmMzNjOWVjOTEyYmI2NGM3MjU2MmY1ZmU1YSIsInZlcnNpb24iOjF9.sUGKAQSY8k7JFCxCSjGC1Y8N6C-9zbeqALTr45erB30Q4yO7Poq9V2WoJQ3Eh6JJhHC8-V_REJtujCxmIJUPCQ
+    - type: rouge
       value: <TODO>
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjYyNjk0NzdjMTViZmJkNGFlMDFhNWJjMjYyZDhjMzMzMjAyNmNiMzc0YTk5ZDI2ZTNlZDc1ZTE0ZTc1ODJkZCIsInZlcnNpb24iOjF9.m9PCgMGsGjD42_J2gokmzzHrh-sIHLf2txvmHzbNoV4vx_7JfF-LNoodgd_D6rPuJrebld5w6JwMgSI4abPQDg
+    - type: rouge
       value: <TODO>
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDMyODhjMjZlMjQzMDE0NDUyZjg3YjUyYmFmYmQzMjNkZGE5YjlhNzU4MDdhMmQwZjJjNjE2ZjZlMjQzNWJlYSIsInZlcnNpb24iOjF9.I_xeOcRbe_g3fLBeEraHI7JsxBz_rKlm893dylB0HGD4UyHuM5qtYyLu5p2ohhIoXX_W-PC-AFF-mlrUcBZhBw
+    - type: loss
       value: <TODO>
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWZiZGExY2M4NmM3ODhhZWVjYjk1MTg0M2YwMzc2Y2JkMmYxZjVkNzk0MDVhY2I2MzIyMDJiOWE4MmM3ZjIzYyIsInZlcnNpb24iOjF9.lFkphS1uVSwwr8h8dOq-AOghE8RYh9QRKL1f4QPzxxp8q-TiKEDwsWlyjnAaWXpUjNbMVMDETGiP5-pzKOomBg
+    - type: gen_len
       value: <TODO>
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmQwYmU0MjU5MTMxNGNiYWNmZGYwNDRmZGU2M2E0MTJmMTVjOThhZGM4NjU4MTI4ZDk5YzY4YjkyMDNlYzcxZSIsInZlcnNpb24iOjF9.6ZRzKoP9RGfr95lRPxJlETH-tbNZ-evNv8_AdkwULllUyIlpanmU0BF57EJHkIf4CYYuyjC_phaCfplAH8rmBQ
   - task:
       type: summarization
       name: Summarization
@@ -52,30 +58,36 @@ model-index:
       config: default
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 36.7656
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2QzMDg4NTM0ZTc5MjAzNTY4MmY1YTRiMWI3M2I2NDdjMTM4ZGNhYzZhOWQzMWI0MjJlYmU3MTg0ZjVjMTEyZSIsInZlcnNpb24iOjF9.AuKHql0LQs0zDQNn7zvySnX50GAC8jEWyYz-LtBgWj0dcad86J8yfHbIDswmgx2ur0S3yttw72qNExag_Fw7Dw
+    - type: rouge
       value: 14.6898
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTE3ZTExY2M3MTIwMWY0ODRkZDI1YjU2ZjRkOGJjOGQyYjcxMTMxOWExN2Q0OGNkZmNiYzYzYzVhODY4YzEwOSIsInZlcnNpb24iOjF9.F1Q17sa8IAsW8ouQ2VDLq_VvHDxjuMjVU3rMfvkbmKxAjTDKVTiaG6Eg9uSKIYzgJoDSsxhsZcjH-J0gGQv3Dg
+    - type: rouge
       value: 30.0646
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzI1NjE0NmI5Nzc3ODFiNDI5YzVhNjUzNzU1NzA0ZDMwMjFjZDE1YzUxNjZmZTAwZTM0MmVmN2ZkYWUwMjBiZSIsInZlcnNpb24iOjF9.xehN8zOV6050WvoLZIJ-l2zB93jWY_ugcydDDqV06XwdKwZ7l0TI8BoLDOO7Mw7dRmHOWLNruDJZnOnW3_3pCQ
+    - type: rouge
       value: 30.0563
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmU0OTVhYTY0ZDJmOTU3OWE5MzgxYzdhNmQ3MjM3YzM2MGIzOGViY2ZkMTI1ZWI4NDMwOTlkODBjOGE4NTE4ZCIsInZlcnNpb24iOjF9.FtNN06HKSgEB1tiWpToEVnNfzhQs9ZR59386YynOY6T6oKWxbIiRyItzYXobNw96lg5c2sE4vdJSfdtbBpkyDA
+    - type: loss
       value: 1.6373405456542969
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTVjYzI0MmMyY2IzYTE0NDUxY2FiMDM4Mjk2NTI1NTk0NjFiYTY2OWMxODRjNWJhYjU4ZWU5OTk4Y2E5N2RkOSIsInZlcnNpb24iOjF9.Cz5AQ-B8IAXmf1Xc_7UJ0pI9XKYHxDEwmoP3ZFsS2Wmbk1pUB8o_Y8AErBR8-Q60qR_ndw8eSwrI0EnPohYHCw
+    - type: gen_len
       value: 18.6054
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWRlMjM5MzAyMjEzYzdkODFmNDk4NDg5NWM4NWIxMTU4YWMxNzZjMGFjOWJiMDdkMjQyMTY0ZGFmYzA2OTA0YiIsInZlcnNpb24iOjF9.IFiGJEsyD7Uhj8bo9SsAgibk9qCXZH6IWaLKULLxBz5N8WXF2vc2Mfg5OThEzdrydPhJInRgp0jd8m-kF5nNCA
 ---
 
 # T5-large Summarization Model Trained on the combined XSUM-CNN Daily Mail Dataset