ColossalAI
                                
                                
                                
                                    ColossalAI copied to clipboard
                            
                            
                            
                        experience_batch_size in PPO training
ColossalAI/applications/Chat/coati/trainer/ppo.py: replay_buffer = NaiveReplayBuffer(train_batch_size, buffer_limit, buffer_cpu_offload) Because this is constructing experimental data,should the train_batch_size in the above code be experience_batch_size?