[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

applications/ColossalChat/coati/dataset/loader.py

@@ -359,8 +359,6 @@ def apply_chat_template_and_mask(
 
     system_prompt = "You are a helpful assistant. The assistant first thinks about the reasoning process in the mind and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and<answer> </answer> tags, respectively, i.e., <think> reasoning process here </think><answer> answer here </answer>. Now the user asks you to solve a math problem that involves reasoning. After thinking, when you finally reach a conclusion, clearly output the final answer without explanation within the <answer> </answer> tags, i.e., <answer> 123 </answer>.\n\n"
 
-    
-
     system_element = {
         "role": "system",
         "content": system_prompt,

applications/ColossalChat/coati/distributed/consumer.py

@@ -1,6 +1,7 @@
+import os
 from contextlib import nullcontext
 from typing import Any, Dict, Optional
-import os
+
 import ray
 import ray.util.collective as cc
 import torch
@@ -34,7 +35,7 @@ class BaseConsumer:
         plugin_config: Dict[str, Any],
         microbatch_size: int = 1,
         save_interval: int = 100,
-        save_dir: str = "./model"
+        save_dir: str = "./model",
     ):
         self.num_producers = num_producers
         self.num_episodes = num_episodes

applications/ColossalChat/coati/distributed/grpo_consumer.py

@@ -79,7 +79,7 @@ class GRPOConsumer(BaseConsumer):
 
         self.policy_loss_fn = PolicyLoss()
         self.global_step = 0
-        if use_wandb and  self.rank == 0:
+        if use_wandb and self.rank == 0:
             self.wandb_run = wandb.init(project="GRPO-Test", sync_tensorboard=True)
 
     def setup(self):