Add evaluation results on the pubmed config and train split of scientific_papers (#7)

- Add evaluation results on the pubmed config and train split of scientific_papers (f6be60c9932737d2a06032f56aa692e12de39f3c)


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

README.md

@@ -1,8 +1,8 @@
 ---
 language: en
+license: mit
 tags:
 - summarization
-license: mit
 model-index:
 - name: SamuelAllen123/t5-efficient-large-nl36_fine_tune_sum_V2
   results:
@@ -15,29 +15,29 @@ model-index:
       config: samsum
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 50.5049
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+    - type: rouge
       value: 25.6469
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+    - type: rouge
       value: 41.7544
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+    - type: rouge
       value: 46.2055
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+    - type: loss
       value: 1.5158178806304932
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+    - type: gen_len
       value: 24.0342
+      name: gen_len
       verified: true
   - task:
       type: summarization
@@ -48,29 +48,29 @@ model-index:
       config: 3.0.0
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 34.4055
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+    - type: rouge
       value: 14.127
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+    - type: rouge
       value: 24.3353
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+    - type: rouge
       value: 31.6582
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+    - type: loss
       value: 2.4456119537353516
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+    - type: gen_len
       value: 45.928
+      name: gen_len
       verified: true
   - task:
       type: summarization
@@ -81,30 +81,69 @@ model-index:
       config: samsum
       split: train
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 54.933
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+    - type: rouge
       value: 31.7965
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+    - type: rouge
       value: 47.0057
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+    - type: rouge
       value: 51.2027
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+    - type: loss
       value: 1.130684494972229
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+    - type: gen_len
       value: 23.7989
+      name: gen_len
       verified: true
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: scientific_papers
+      type: scientific_papers
+      config: pubmed
+      split: train
+    metrics:
+    - type: rouge
+      value: 23.6698
+      name: ROUGE-1
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTg4OTMwYjkyNmU1ZjdmN2Q4MWE4YzFkZjUyMDZhNDNhYjBkODg3ZjI5NDQxMTcyNDUyMzkwNDZlNjNhZGRiOSIsInZlcnNpb24iOjF9.0kRK7iA642z0YWAH81v1_-pil6TyM3bezGfZtqGev5O7AgGkxzfQaIDNhkVVvVIJdUPJFD7L36XyLx3AWO5BCQ
+    - type: rouge
+      value: 7.5691
+      name: ROUGE-2
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2Q2MDc1ZjZlYjRmZDZkNjY3MmFhODAzZWUwZjA1M2RlZGUwYTY2ZjM2ZTM1NzQ3YjAxMDFiMWZlMGMwNTgyOCIsInZlcnNpb24iOjF9._Y59aEEGLn0Ij622V8Rwljp-h4uTuCfoPgJdvMN6GvCyKRzwugHo8tedfTpbTAb6cicjiWjKvKurqXTjpw1KAw
+    - type: rouge
+      value: 15.6071
+      name: ROUGE-L
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjMwM2Q2ODYwZWE4MzNhNDNlNzlhNjU2NGUxYjlhNDM3MzM5MmJjNzU4YTYxNzI4ZmQ3YzQ1YjMzMDZkMTQ4ZCIsInZlcnNpb24iOjF9.zyfiVsuCEXCTkGAqNxCZ8hTKVxAE0JmJRbNZ04HoBi7qYFB13_7JTB6tOvAEH34W-2yvpOs4cBsFqtXg7RvnCA
+    - type: rouge
+      value: 21.4565
+      name: ROUGE-LSUM
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTE4MjVlZjI5NDBkZjRmODA3MmIzY2I0YWUwZjEyMzYwNjFjNTY3N2NjMmY3ZThlODBjN2VhZWZlODliZmEyZSIsInZlcnNpb24iOjF9.RFZbr5R9cJtrhzWMKys62fiBxKv8MYe6_115NBjEZ6wOwzVih5SdJE8r2EK-1wdCMF_jLGPYQvZ-zyj3KHGWCw
+    - type: loss
+      value: 3.9369945526123047
+      name: loss
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTc3MzMwYTg5OWIyZGQxNGJlYzExNTY0MjUyY2M5M2NiOGQ2ODI0MWFiMzJjYWY4ZGNkZmY2MmUyZjVjODRiYSIsInZlcnNpb24iOjF9.iDxSfTwZRV5VboHLjF4a47kPXagG7bY78WIejIM37ykpksXxVYssZlmK6UxtkEmZuWypqbQjz6oOjTjy6x3tDQ
+    - type: gen_len
+      value: 65.9987
+      name: gen_len
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODdmYzFiNzU3N2VlMWMyMGEwZmFkZmExZWRlN2NjNWI3ZGJjNmYzMWExYWM5MWY2MzJkMmY0ZGE2NjFjMjRjYyIsInZlcnNpb24iOjF9.3ByM1s1Ux-PDBBnf6i3FUtFLzpmZXcikIfrsR3vTIi9567r789Wm8sW81blFHNfnST-ZHQxPKJOuv4ho8S4eCg
 ---
 *NOT SELF REPORTED VALUES FOR THE LEADERBOARD, I HAVE NO CLUE WHY ITS BROKE. CHECK PULL REQUEST*