Update README.md

README.md

@@ -79,7 +79,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [S
 - **Maximum Sequence Length:** 512 tokens
 - **Output Dimensionality:** 384 tokens
 - **Similarity Function:** Cosine Similarity
-<!-- - **Training Dataset:** Unknown -->
+- **Training Dataset:** scraped astronomy papers at the NLP for Space Science workshop.
 - **Language:** en
 - **License:** apache-2.0
 
@@ -171,6 +171,8 @@ You can finetune this model on your own dataset.
 
 ### Training Dataset
 
+The dataset is made of scrapes papers in astronomy, including abstract, introduction and conclusions. They are divided into sentences using nklt. We then duplicate them and train using the same senrence for positive and anchor. We are using SimSCE.
+
 #### Unnamed Dataset
 
 
@@ -326,17 +328,6 @@ You can finetune this model on your own dataset.
 
 | Epoch  | Step  | Training Loss |
 |:------:|:-----:|:-------------:|
-| 0.0077 | 100   | 0.4784        |
-| 0.0154 | 200   | 0.2415        |
-| 0.0231 | 300   | 0.0424        |
-| 0.0307 | 400   | 0.021         |
-| 0.0384 | 500   | 0.0149        |
-| 0.0461 | 600   | 0.0081        |
-| 0.0538 | 700   | 0.0084        |
-| 0.0615 | 800   | 0.0067        |
-| 0.0692 | 900   | 0.0034        |
-| 0.0769 | 1000  | 0.0025        |
-| 0.0846 | 1100  | 0.0016        |
 | 0.0077 | 100   | 0.0025        |
 | 0.0154 | 200   | 0.0032        |
 | 0.0231 | 300   | 0.0026        |
@@ -768,6 +759,8 @@ You can finetune this model on your own dataset.
 }
 ```
 
+#Add SimSCE reference
+
 <!--
 ## Glossary