Update README.md

README.md

@@ -21,7 +21,7 @@ We explore supervised multitask pre-training by proposing ***Instruction Pre-Tra
 **************************** **Updates** ****************************
 * 2024/8/29: Updated [guidelines](https://huggingface.co/instruction-pretrain/finance-Llama3-8B) on evaluating any 🤗Huggingface models on the domain-specific tasks
 * 2024/7/31: Updated pre-training suggestions in the `Advanced Usage` section of [instruction-synthesizer](https://huggingface.co/instruction-pretrain/instruction-synthesizer)
-* 2024/7/15: We scaled up the pre-trained tokens from 100B to 250B, with the number of synthesized instruction-response pairs reaching 500M. Below, we show the performance trend on downstream tasks throughout the pre-training process:
+* 2024/7/15: We scaled up the pre-trained tokens from 100B to 250B, with the number of synthesized instruction-response pairs reaching 500M. The performance trend on downstream tasks throughout the pre-training process:
 <p align='left'>
     <img src="https://cdn-uploads.huggingface.co/production/uploads/66711d2ee12fa6cc5f5dfc89/0okCfRkC6uALTfuNxt0Fa.png" width="500">
 </p>
@@ -83,7 +83,7 @@ You can use the following script to reproduce our results and evaluate any other
 
 2). Evaluate the Model
    ```bash
-   # Select the domain from ['biomedicine', 'finance', 'law']
+   # Select the domain from ['biomedicine', 'finance']
    DOMAIN='finance'
   
    # Specify any Huggingface LM name (Not applicable to models requiring specific prompt templates)