small fix README

README.md

@@ -98,7 +98,7 @@ print(similarities.shape)
 
 To achieve generic text embedding performance across a wide range of domains, we performed contrastive training on weakly-supervised data consisting of our own web-crawled data and open data.
 
-#### Dataset
+#### Datasets
 
 |dataset|counts|
 |:-:|:-:|
@@ -118,9 +118,9 @@ To achieve generic text embedding performance across a wide range of domains, we
 
 ### Step2: Supervised Fine-tuning
 
-To enable the model to learn a more accurate query-document similarity, we performed supervised fine-tuning using the following dataset.
+To enable the model to learn a more accurate query-document similarity, we performed supervised fine-tuning using the following datasets.
 
-#### Dataset
+#### Datasets
 
 |dataset|counts|
 |:-:|:-:|