mzio/tw-sft-coin-collector-easy-hi

--- 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: done dtype: bool - name: reward dtype: float64 - name: is_train dtype: bool - name: tools list: - name: description dtype: string - name: name dtype: string - name: parameters struct: - name: properties struct: - name: direction struct: - name: description dtype: string - name: enum list: string - name: type dtype: string - name: required list: string - name: type dtype: string - name: type dtype: string - name: system_prompt dtype: string - name: unique_data_sample_id dtype: int64 - name: timestep dtype: int64 - name: generation_id dtype: int64 - name: return_ dtype: float64 - name: advantage dtype: float64 - name: split dtype: string splits: - name: train num_bytes: 14578337 num_examples: 1220 download_size: 13999692 dataset_size: 14578337 configs: - config_name: default data_files: - split: train path: data/train-* ---