diff --git a/applications/Chat/examples/README.md b/applications/Chat/examples/README.md
index af8ded005..0083dc372 100644
--- a/applications/Chat/examples/README.md
+++ b/applications/Chat/examples/README.md
@@ -146,11 +146,15 @@ torchrun --standalone --nproc_per_node=4 train_prompts.py \
          --pretrain "/path/to/LLaMa-7B/" \
          --model 'llama' \
          --strategy colossalai_zero2 \
-         --prompt_path /path/to/your/prompt_dataset \
+         --prompt_dataset /path/to/your/prompt_dataset \
          --pretrain_dataset /path/to/your/pretrain_dataset \
          --rm_pretrain /your/pretrain/rm/defination \
          --rm_path /your/rm/model/path
 ```
+
+Prompt dataset: the instruction dataset mentioned in the above figure which includes the instructions, e.g. you can use [seed_prompts_ch.jsonl](https://github.com/XueFuzhao/InstructionWild/blob/main/data/seed_prompts_ch.jsonl) or [seed_prompts_en.jsonl](https://github.com/XueFuzhao/InstructionWild/blob/main/data/seed_prompts_en.jsonl) in InstructionWild.  
+Pretrain dataset: the pretrain dataset including the instruction and corresponding response, e.g. you can use the [InstructWild Data](https://github.com/XueFuzhao/InstructionWild/tree/main/data) in stage 1 supervised instructs tuning.
+
 ### Arg List
 - --strategy:          the strategy using for training, choices=['naive', 'ddp', 'colossalai_gemini', 'colossalai_zero2'], default='naive'
 - --model:             model type of actor, choices=['gpt2', 'bloom', 'opt', 'llama'], default='bloom'
@@ -159,7 +163,7 @@ torchrun --standalone --nproc_per_node=4 train_prompts.py \
 - --rm_pretrain:       pretrain model for reward model, type=str, default=None
 - --rm_path:           the path of rm model, type=str, default=None
 - --save_path:         path to save the model, type=str, default='output'
-- --prompt_path:       path of the prompt dataset, type=str, default=None
+- --prompt_dataset:       path of the prompt dataset, type=str, default=None
 - --pretrain_dataset:  path of the ptx dataset, type=str, default=None
 - --need_optim_ckpt:   whether to save optim ckpt, type=bool, default=False
 - --num_episodes:      num of episodes for training, type=int, default=10
diff --git a/applications/Chat/examples/test_ci.sh b/applications/Chat/examples/test_ci.sh
index 32f5858a5..a86e2295a 100755
--- a/applications/Chat/examples/test_ci.sh
+++ b/applications/Chat/examples/test_ci.sh
@@ -99,7 +99,7 @@ torchrun --standalone --nproc_per_node=2 ${BASE}/train_reward_model.py \
 
 rm -rf ${BASE}/rm_ckpt.pt
 
-torchrun --standalone --nproc_per_node=2 ${BASE}/train_prompts.py --prompt_path $PROMPT_PATH --pretrain_dataset $PRETRAIN_DATASET \
+torchrun --standalone --nproc_per_node=2 ${BASE}/train_prompts.py --prompt_dataset $PROMPT_PATH --pretrain_dataset $PRETRAIN_DATASET \
         --strategy colossalai_zero2 --num_episodes 1 --max_timesteps 2 \
         --update_timesteps 2 --max_epochs 1 --train_batch_size 2 \
         --pretrain 'facebook/opt-350m' --model opt \
@@ -108,7 +108,7 @@ torchrun --standalone --nproc_per_node=2 ${BASE}/train_prompts.py --prompt_path
         --save_path ${BASE}/actor_checkpoint_prompts.pt
 rm -rf ${BASE}/rm_ckpt_opt.pt
 
-torchrun --standalone --nproc_per_node=2 ${BASE}/train_prompts.py --prompt_path $PROMPT_PATH --pretrain_dataset $PRETRAIN_DATASET \
+torchrun --standalone --nproc_per_node=2 ${BASE}/train_prompts.py --prompt_dataset $PROMPT_PATH --pretrain_dataset $PRETRAIN_DATASET \
          --strategy colossalai_zero2 --num_episodes 1 --max_timesteps 2 \
          --update_timesteps 2 --max_epochs 1 --train_batch_size 2 \
          --pretrain 'gpt2' --model gpt2 \
diff --git a/applications/Chat/examples/train_prompts.py b/applications/Chat/examples/train_prompts.py
index c0455f3a7..292caa1b3 100644
--- a/applications/Chat/examples/train_prompts.py
+++ b/applications/Chat/examples/train_prompts.py
@@ -139,7 +139,7 @@ def main(args):
 
     data_collator = DataCollatorForSupervisedDataset(tokenizer=tokenizer)
 
-    prompt_dataset = PromptDataset(tokenizer=tokenizer, data_path=args.prompt_path, max_datasets_size=16384)
+    prompt_dataset = PromptDataset(tokenizer=tokenizer, data_path=args.prompt_dataset, max_datasets_size=16384)
     if dist.is_initialized() and dist.get_world_size() > 1:
         prompt_sampler = DistributedSampler(prompt_dataset, shuffle=True, seed=42, drop_last=True)
     else:
@@ -204,7 +204,7 @@ def main(args):
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument('--prompt_path', type=str, default=None, help='path to the prompt dataset')
+    parser.add_argument('--prompt_dataset', type=str, default=None, help='path to the prompt dataset')
     parser.add_argument('--pretrain_dataset', type=str, default=None, help='path to the pretrained dataset')
     parser.add_argument('--strategy',
                         choices=['naive', 'ddp', 'colossalai_gemini', 'colossalai_zero2'],
diff --git a/applications/Chat/examples/train_prompts.sh b/applications/Chat/examples/train_prompts.sh
index 8e1ce67ec..7f3b2636c 100755
--- a/applications/Chat/examples/train_prompts.sh
+++ b/applications/Chat/examples/train_prompts.sh
@@ -17,4 +17,4 @@ set_n_least_used_CUDA_VISIBLE_DEVICES 2
 
 # torchrun --standalone --nproc_per_node=2 train_prompts.py prompts.csv --strategy colossalai_zero2
 
-torchrun --standalone --nproc_per_node=2 train_prompts.py --prompt_path /path/to/data.json --strategy colossalai_zero2
+torchrun --standalone --nproc_per_node=2 train_prompts.py --prompt_dataset /path/to/data.json --strategy colossalai_zero2