Add evaluation results on the autoevaluate--wmt16-ro-en-sample config and test split of autoevaluate/wmt16-ro-en-sample

README.md

@@ -11,16 +11,40 @@ model-index:
 - name: translation
   results:
   - task:
-      name: Sequence-to-sequence Language Modeling
       type: text2text-generation
+      name: Sequence-to-sequence Language Modeling
     dataset:
       name: wmt16
       type: wmt16
       args: ro-en
     metrics:
-    - name: Bleu
-      type: bleu
+    - type: bleu
       value: 28.5866
+      name: Bleu
+  - task:
+      type: translation
+      name: Translation
+    dataset:
+      name: autoevaluate/wmt16-ro-en-sample
+      type: autoevaluate/wmt16-ro-en-sample
+      config: autoevaluate--wmt16-ro-en-sample
+      split: test
+    metrics:
+    - type: bleu
+      value: 2.7663
+      name: BLEU
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjRlMmFiNmViZmFmYTViZmQ4NWIwNDQ2NmI4MDBiZjg1MzZjMWZkMzY0YjA2ZjE2ZTZhZjI5MWVmOGZhOGRmNiIsInZlcnNpb24iOjF9.9may0WjvZnNl1ulo8rxh3Fl_g1om6QRC7ZklgV2rZ_-w8_ZhA7v62SEopmkIPLX_cpWinwKzg-p-2e18XDgvBQ
+    - type: loss
+      value: 4.943170070648193
+      name: loss
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWQ2MmIwMjcxMDJhOGI1ODE5NjA2ZjViMDYxMjlhY2MzODIwMDI1YWU5NzExMTBjYWUxOTNhYzU1OTc5OGFjNyIsInZlcnNpb24iOjF9._ogVvMQzTw3w77SHzZx-lfKDqoBb3gxjdztg5TFKn_FujSxRw14NhcZxYrpEeZmWa7rcMshhzKFBjTYSaLxIAg
+    - type: gen_len
+      value: 40.35
+      name: gen_len
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWUwYWNkMmZkM2MxNjJjNmU1MTYzYzliMjU0NGFkZGM2MjBiNDkyNzMxYWJiM2ViNDYxZWMyMDFhMDdiNTJlYiIsInZlcnNpb24iOjF9.PBIJpF-XsDMCV1XrQBmFN_kjUKwlz4bqgNm698AtMgYTrsfkwgOq_CItdgjGK1aXzRqZMfGOzP2NIPeiy3dMBg
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You