Update README.md

README.md

@@ -175,10 +175,12 @@ All of our models attained good accuracy values, in the range of 0.65, as can be
 
 We are currently in the process of applying our language models to downstream tasks.
 
-**SQUAD-es**  
+
+## SQUAD-es
 Using sequence length 128 we have achieved exact match 50.96 and F1 68.74.
 
-**POS** 
+
+## POS
 All models trained with max length 512 and batch size 8, using the CoNLL 2002 dataset. 
 
 <figure>
@@ -200,7 +202,7 @@ All models trained with max length 512 and batch size 8, using the CoNLL 2002 da
 </figure>
 
 
-**NER** 
+## NER 
 All models trained with max length 512 and batch size 8, using the CoNLL 2002 dataset. 
 
 <figure>
@@ -222,7 +224,7 @@ All models trained with max length 512 and batch size 8, using the CoNLL 2002 da
 </figure>
 
 
-**PAWS-X** 
+## PAWS-X 
 All models trained with max length 512 and batch size 8. The accuracy values in this case are a bit surprising (given some models are below 0.60 while others are close to 0.90), so these were run 3 times, with very similar results (these are the metrics for the last run).
 
 <figure>
@@ -243,7 +245,8 @@ All models trained with max length 512 and batch size 8. The accuracy values in
 <caption>Table 5. Results for PAWS-X.</caption>
 </figure>
 
-**CNLI** 
+
+## CNLI
 All models trained with max length 256 and batch size 16.
 
 <figure>