Updated README.md

README.md

@@ -70,19 +70,19 @@ tar -xvf /path/to/folder/gtg_pretrained.tar.gz
 ```  
   
 #### Clone the repository  
-Clone the repository for source code  
+Clone the repository source code
 ```shell  
 git clone https://git.pavanmandava.com/pavan/master-thesis.git
-```  
-
-Pull the changes from remote (if local is behind the remote)  
-```shell  
-git pull
-```  
+```
 
 Change directory  
 ```shell  
 cd master-thesis
+``` 
+
+Pull the changes from remote (if local is behind the remote)  
+```shell  
+git pull
 ```  
   
 #### Set Environment variables  
@@ -99,6 +99,8 @@ Edit the [set_env.sh](set_env.sh) file and set the paths (as required) for the f
 `SAVED_MODELS_PROMPT` - Path for saving the trained prompt-based models (after each epoch)
 
 `OUTPUTS_DIR_PROMPT` - Path for storing the prompt model outputs (generations)
+
+> :information_source: **Note**: Change the paths of each environment variable and make sure it matches your local system. Invalid/Wrong paths may lead to errors in the training/testing script.
   
 ```shell  
 nano set_env.sh
@@ -179,7 +181,7 @@ The data for training the prompt learning model is available under [data/prompt-
 `create_dataset.py` ([link](utils/create_dataset.py)) has the scripts for converting/creating the data for training the prompt-based model.
 
 > **Note:**
-> Running `create_dataset.py` can take some time as it has to download, install and run Stanford CoreNLP `stanza` package.
+> Running `create_dataset.py` can take some time as it needs to download, install and run Stanford CoreNLP `stanza` package.
 > All the data required for training the prompt-based model is available under [data](data) directory of this repo.
 
 ### Install the requirements