update model card README.md

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: mit
 tags:
 - generated_from_trainer
@@ -13,15 +15,13 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE STSB
       type: glue
-      config: stsb
-      split: train
       args: stsb
     metrics:
     - name: Spearmanr
       type: spearmanr
-      value: 0.9076586309161793
+      value: 0.9092158650855444
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,12 +29,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # roberta-base-stsb
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the glue dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4311
-- Pearson: 0.9096
-- Spearmanr: 0.9077
-- Combined Score: 0.9086
+- Loss: 0.4221
+- Pearson: 0.9116
+- Spearmanr: 0.9092
+- Combined Score: 0.9104
 
 ## Model description