Update README.md

README.md

@@ -31,22 +31,32 @@ HateBERTimbau is a transformer-based encoder model for identifying hate speech i
 - **Language:** Portuguese
 - **Finetuned from model:** [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased)
 
+<br>
+
 ## Uses
 
 [More Information Needed]
 
-## Training Data
+<br>
+
+## Training
+
+### Data
 
 229,103 tweets associated with offensive content were used to retrain the base model.
 
-## Training Hyperparameters
+### Training Hyperparameters
 
 - Batch Size: 4 samples
 - Epochs: 100
 - Learning Rate: 5e-5 with Adam optimizer
 - Maximum Sequence Length: 512 sentence pieces
 
-## Testing Data
+<br>
+
+## Testing
+
+### Data
 
 We used two different datasets for testing, one for YouTube comments [here](https://huggingface.co/datasets/knowhate/youtube-test) and another for Tweets [here](https://huggingface.co/datasets/knowhate/twitter-test).
 
@@ -58,13 +68,15 @@ Twitter Test Set:
 - Total nº of tweets: 805
 - % Hate Speech: 20.62%
 
-## Results
+### Results
 
 | Dataset         | Precision  | Recall    | F1-score     |
-|:-----------------|:----------- |:-----------|:--------------|
+|:----------------|:-----------|:----------|:-------------|
 | **YouTube**     | 0.928      | 0.108     | **0.193**    | 
 | **Twitter**     | 0.686      | 0.211     | **0.323**    |
 
+<br>
+
 ## BibTeX Citation
 
 ``` latex
@@ -82,7 +94,7 @@ copyright = {embargoed-access},
 }
 ```
 
-
+<br>
 
 ## Acknowledgements