Closed MurrayTom closed 3 days ago
Hello, I want to run train_ppo_llama.sh on 4 A100 80G. Do I need to reconfigure the GPU allocation of the 4 models?
train_ppo_llama.sh shares gpus for all models, you just need to reconfigure the GPUs in train_ppo_llama_ray.sh
Hello, I want to run train_ppo_llama.sh on 4 A100 80G. Do I need to reconfigure the GPU allocation of the 4 models?