Update README.md

README.md

@@ -35,14 +35,14 @@ This version includes the optimizer, allowing you to resume training using the H
 
 ## Continual Training Tutorial
 
-### Step 1: Modify the `config.json`
+### Step 1: Modify the `trainer_state.json`
 
-Due to the implementation of Hugging Face Trainer, certain parameters are stored in the `config.json` file and cannot be modified through the Trainer's command-line arguments. Therefore, you need to update these parameters in the `config.json` file first, particularly:
+Due to the implementation of Hugging Face Trainer, certain parameters are stored in the `trainer_state.json` file and cannot be modified through the Trainer's command-line arguments. Therefore, you need to update these parameters in the `trainer_state.json` file first, particularly:
 
 - **`save_steps`**: The frequency of saving intermediate checkpoints.
 - **`train_batch_size`**: The batch size per GPU (equivalent to `per_device_train_batch_size` in the Trainer). We used a batch size of 1008 (approximately 4M tokens) during the stable training stage. Maintaining this same batch size is equally important for training effectiveness.
 
-Below is an example of a properly configured `config.json` file:
+Below is an example of a properly configured `trainer_state.json` file:
 
 ```json
 {