prm
Datasets
All datasets matching “prm”PRM800Khttps://github.com/openai/prm800k/tree/main
prm800k_rlhf
Dataset Card for "prm800k_rlhf"
More Information needed
PRM-agent-rl-artifacts
PRM-agent-rl-artifacts
Training rollouts and evaluation outputs for the GRPO agent runs in this project.
Each rollout file is one optimizer step; each line is one sampled trajectory with
its decoded prompt, response and reward.
Contents
rollouts/search_r1_qwen3_8b_4gpu — Search-R1 / Qwen3-8B outcome-GRPO training rollouts
rollouts/search_r1_qwen3_8b_perturnnorm — Search-R1 / Qwen3-8B Process-GRPO (per-turn-norm) training rollouts
rollouts/alfworld_qwen3_8b_gigpo… See the full description on the dataset page: https://huggingface.co/datasets/wckwan/PRM-agent-rl-artifacts.VL-PRM300K-train
Dataset Card for VL-PRM300K-train
Dataset Summary
VL-PRM300K-train is a postprocessed version of VL-PRM300K, ready to be used with training pipelines using HuggingFace Trainer and TRL.
Usage
# pip install -q datasets
from datasets import load_dataset
ds = load_dataset("ob11/VL-PRM300K-train")["train"]
Dataset Structure
Data Fields
The data fields are:
messages: Reasoning trace formatted for supervised finetuning with HuggingFace… See the full description on the dataset page: https://huggingface.co/datasets/ob11/VL-PRM300K-train.veri_seti_adifairness-prm-training-data