workload: "grpo"

submission_id: ""

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

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

train_file: "/private/common/datasets/gsm8k/train.parquet"
val_file: "/private/common/datasets/gsm8k/test.parquet"

nnodes: 2
n_gpus_per_node: 4

total_epochs: 1
total_training_steps: 10

save_freq: 10
test_freq: -1