diff --git a/verifiers/examples/math_python.py b/verifiers/examples/math_python.py index 41a75e4302..54f9c47071 100644 --- a/verifiers/examples/math_python.py +++ b/verifiers/examples/math_python.py @@ -1,11 +1,11 @@ import verifiers as vf from verifiers.tools import python -from verifiers.utils import load_example_dataset +from verifiers.utils.data_utils import load_example_dataset """ Multi-GPU training (single node, 4 training + 4 inference) -CUDA_VISIBLE_DEVICES=0,1,2,3 vf-vllm --model 'willcb/Qwen2.5-7B-Math-Python-SFT' --tensor_parallel_size 4 +CUDA_VISIBLE_DEVICES=0,1,2,3 vf-vllm --model 'willcb/Qwen2.5-7B-Math-Python-SFT' --tensor-parallel-size 4 CUDA_VISIBLE_DEVICES=4,5,6,7 accelerate launch --config-file configs/zero3.yaml verifiers/examples/math_train.py """ @@ -50,7 +50,8 @@ system_prompt=TOOL_PROMPT, few_shot=[], tools=[python], - max_steps=3 + max_steps=3, + sampling_args={"extra_body": {"logprobs": True}} ) print(vf_env.system_prompt)