Update README.md

Training data is actually 3,200 responses coded. Missed the 200 all researchers coded jointly in this count

README.md

@@ -144,7 +144,7 @@ As the model was fine-tuned from SimCSE, itself fine-tuned from BERT, it will re
 
 #### Training Data 
 
-The model was fine-tuned on 3,000 labeled open-ended responses from [RANDS during COVID 19 Rounds 1 and 2](https://www.cdc.gov/nchs/rands/index.htm). The base SimCSE BERT model was trained on BookCorpus and English Wikipedia. 
+The model was fine-tuned on 3,200 labeled open-ended responses from [RANDS during COVID 19 Rounds 1 and 2](https://www.cdc.gov/nchs/rands/index.htm). The base SimCSE BERT model was trained on BookCorpus and English Wikipedia. 
 
 #### Training procedure