mzio/aprm-insurance-gpt5m_med-gs4-s0-r1-train

--- dataset_info: features: - name: state list: - name: content dtype: string - name: role dtype: string - name: action struct: - name: content dtype: string - name: role dtype: string - name: next_obs list: - name: content dtype: string - name: role dtype: string - name: state_len dtype: int64 - name: temperature dtype: float64 - name: reward dtype: float64 - name: done dtype: bool - name: truncated dtype: bool - name: timestep dtype: int64 - name: try_step dtype: int64 - name: batch_id dtype: int64 - name: unique_data_sample_id dtype: int64 - name: generation_id dtype: int64 - name: split dtype: string - name: return_ dtype: float64 - name: advantage dtype: int64 - name: return_is_computed dtype: bool - name: advantage_is_computed dtype: bool - name: constant_reward_group dtype: bool - name: tools list: - name: description dtype: string - name: name dtype: string - name: parameters struct: - name: properties struct: - name: query struct: - name: description dtype: string - name: type dtype: string - name: table struct: - name: description dtype: string - name: type dtype: string - name: table_name struct: - name: description dtype: string - name: type dtype: string - name: text struct: - name: description dtype: string - name: type dtype: string - name: required list: string - name: type dtype: string - name: type dtype: string - name: action_prob dtype: float64 - name: system_prompt dtype: string splits: - name: train num_bytes: 291577091 num_examples: 13131 download_size: 272663240 dataset_size: 291577091 configs: - config_name: default data_files: - split: train path: data/train-* ---