Update README.md

README.md

@@ -24,9 +24,9 @@ One-off run using a [modified version](https://gist.github.com/bclavie/93d3b161d
 
 w/o extensive tuning, the model trains considerably faster than BERT-base, and gets **+5 Weighted F1**:
 
-## Results
+# Results
 
-### ModernBERT-base-fineweb-edu-example
+## ModernBERT-base-fineweb-edu-example
 
 **Weighted F1: 0.76**
 
@@ -48,7 +48,7 @@ Validation Report:
 weighted avg       0.76      0.76      0.76     46743
 ```
 
-### Original Classifier (https://huggingface.co/HuggingFaceFW/fineweb-edu-classifier):
+## Original Classifier (https://huggingface.co/HuggingFaceFW/fineweb-edu-classifier):
 
 **Weighted F1: 0.71**
 
@@ -71,7 +71,7 @@ weighted avg       0.71      0.71      0.71     46867
 
 (for some reason, the currently available annotated dataset is identical, except that it's missing 124 of the 125 5-rated examples. These are so anecdotal they have no real impact on the weighted metrics.)
 
-## Params
+# Params
 
 Most parameters detailed in the script. Key hparams: