workload: "sft"

submission_id: ""

code_path: "/private/common/code/verl/verl_repo"

model_id: "Qwen/Qwen2.5-0.5B-Instruct"

train_file: "/private/datasets/gsm8k_sft/train.parquet"
val_file: null

nnodes: 2
n_gpus_per_node: 4

total_epochs: 1
total_training_steps: 10

save_freq: 10

# SFT driver 默认不分配 GPU（ray job entrypoint 不指定 entrypoint_num_gpus），因此 driver 侧不要依赖 CUDA
trainer_device: "cpu"