fix nits (#462)

Author: omarespejel

how-to-train-sentence-transformers.md

@@ -29,6 +29,8 @@ Check out this tutorial with the Notebook Companion:
     <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
 </a>
 
+---
+---
 
 Training or fine-tuning a Sentence Transformers model highly depends on the available data and the target task. The key is twofold: 
 1. Understand how to input data into the model and prepare your dataset accordingly.
@@ -50,7 +52,7 @@ In a Sentence Transformer model, you map a variable-length text (or image pixels
 This is how the Sentence Transformers models work:
 
 1. **Layer 1** – The input text is passed through a pre-trained Transformer model that can be obtained directly from the [Hugging Face Hub](https://huggingface.co/models?pipeline_tag=fill-mask&sort=downloads). This tutorial will use the "[distilroberta-base](https://huggingface.co/distilroberta-base)" model. The Transformer outputs are contextualized word embeddings for all input tokens; imagine an embedding for each token of the text.
-2. **Layer 2**: The embeddings go through a pooling layer to get a single fixed-length embedding for all the text. For example, mean pooling averages the embeddings generated by the model.
+2. **Layer 2** - The embeddings go through a pooling layer to get a single fixed-length embedding for all the text. For example, mean pooling averages the embeddings generated by the model.
 
 This figure summarizes the process: