datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
multireward-grpo-gsm8k-rewards-qwen2.5-7b
Multi-Reward GRPO — GSM8K Rewards (Qwen2.5-7B-Instruct)
Raw rollout-level reward observations from the empirical Section of
"Conditioned Multi-Reward Advantage Estimation: A Finite-Sample Analysis".
This is the data that produced the headline Theorem 3 (correlation-dependent
MSE floor) and Proposition 4 (sign-changing conditioning bias) figures on
real LLM rollouts. Each rollout was sampled from Qwen/Qwen2.5-7B-Instruct on
GSM8K test prompts at temperature 0.7.
What's in… See the full description on the dataset page: https://huggingface.co/datasets/eagle0504/multireward-grpo-gsm8k-rewards-qwen2.5-7b.multireward-grpo-gsm8k-rewards
Multi-Reward GRPO — GSM8K Rewards (Qwen2.5-1.5B-Instruct)
Raw rollout-level reward observations from the empirical Section of
"Conditioned Multi-Reward Advantage Estimation: A Finite-Sample Analysis".
This is the data that produced the headline Theorem 3 (correlation-dependent
MSE floor) and Proposition 4 (sign-changing conditioning bias) figures on
real LLM rollouts.
What's in here
For each of 150 GSM8K test prompts, we sampled 16 independent seeds × 32
rollouts… See the full description on the dataset page: https://huggingface.co/datasets/eagle0504/multireward-grpo-gsm8k-rewards.