Mitsuki-Sakamoto/alpaca_farm-deberta-re-pref-64-fil_self_160m_bo2_100_kl_0.1_prm_70m_thr_0.0_seed_3_t_1.0

--- dataset_info: config_name: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1 features: - name: instruction dtype: string - name: input dtype: string - name: output dtype: string - name: preference dtype: int64 - name: output_1 dtype: string - name: output_2 dtype: string - name: reward_model_prompt_format dtype: string - name: gen_prompt_format dtype: string - name: gen_kwargs struct: - name: do_sample dtype: bool - name: max_new_tokens dtype: int64 - name: pad_token_id dtype: int64 - name: top_k dtype: int64 - name: top_p dtype: float64 - name: reward_1 dtype: float64 - name: reward_2 dtype: float64 - name: n_samples dtype: int64 - name: reject_select dtype: string - name: prompt dtype: string - name: chosen dtype: string - name: rejected dtype: string - name: index dtype: int64 - name: filtered_epoch dtype: int64 - name: gen_reward dtype: float64 - name: gen_response dtype: string splits: - name: epoch_0 num_bytes: 43586042 num_examples: 18929 - name: epoch_1 num_bytes: 44069611 num_examples: 18929 - name: epoch_2 num_bytes: 44157422 num_examples: 18929 - name: epoch_3 num_bytes: 44188992 num_examples: 18929 - name: epoch_4 num_bytes: 44205250 num_examples: 18929 - name: epoch_5 num_bytes: 44213298 num_examples: 18929 - name: epoch_6 num_bytes: 44216076 num_examples: 18929 - name: epoch_7 num_bytes: 44219886 num_examples: 18929 - name: epoch_8 num_bytes: 44220500 num_examples: 18929 - name: epoch_9 num_bytes: 44222140 num_examples: 18929 - name: epoch_10 num_bytes: 44221917 num_examples: 18929 - name: epoch_11 num_bytes: 44224390 num_examples: 18929 - name: epoch_12 num_bytes: 44224079 num_examples: 18929 - name: epoch_13 num_bytes: 44224389 num_examples: 18929 - name: epoch_14 num_bytes: 44223860 num_examples: 18929 - name: epoch_15 num_bytes: 44224137 num_examples: 18929 - name: epoch_16 num_bytes: 44225266 num_examples: 18929 - name: epoch_17 num_bytes: 44224771 num_examples: 18929 - name: epoch_18 num_bytes: 44224972 num_examples: 18929 - name: epoch_19 num_bytes: 44225512 num_examples: 18929 - name: epoch_20 num_bytes: 44224996 num_examples: 18929 - name: epoch_21 num_bytes: 44225033 num_examples: 18929 - name: epoch_22 num_bytes: 44225067 num_examples: 18929 - name: epoch_23 num_bytes: 44225465 num_examples: 18929 - name: epoch_24 num_bytes: 44225590 num_examples: 18929 - name: epoch_25 num_bytes: 44226014 num_examples: 18929 - name: epoch_26 num_bytes: 44225889 num_examples: 18929 - name: epoch_27 num_bytes: 44226190 num_examples: 18929 - name: epoch_28 num_bytes: 44225922 num_examples: 18929 - name: epoch_29 num_bytes: 44226092 num_examples: 18929 download_size: 698623999 dataset_size: 1325798768 configs: - config_name: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1 data_files: - split: epoch_0 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_0-* - split: epoch_1 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_1-* - split: epoch_2 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_2-* - split: epoch_3 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_3-* - split: epoch_4 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_4-* - split: epoch_5 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_5-* - split: epoch_6 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_6-* - split: epoch_7 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_7-* - split: epoch_8 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_8-* - split: epoch_9 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_9-* - split: epoch_10 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_10-* - split: epoch_11 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_11-* - split: epoch_12 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_12-* - split: epoch_13 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_13-* - split: epoch_14 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_14-* - split: epoch_15 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_15-* - split: epoch_16 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_16-* - split: epoch_17 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_17-* - split: epoch_18 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_18-* - split: epoch_19 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_19-* - split: epoch_20 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_20-* - split: epoch_21 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_21-* - split: epoch_22 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_22-* - split: epoch_23 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_23-* - split: epoch_24 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_24-* - split: epoch_25 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_25-* - split: epoch_26 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_26-* - split: epoch_27 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_27-* - split: epoch_28 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_28-* - split: epoch_29 path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_29-* ---

原始信息汇总

数据集概述

数据集配置名称

• alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1

数据集特征

• instruction: 数据类型为字符串
• input: 数据类型为字符串
• output: 数据类型为字符串
• preference: 数据类型为int64
• output_1: 数据类型为字符串
• output_2: 数据类型为字符串
• reward_model_prompt_format: 数据类型为字符串
• gen_prompt_format: 数据类型为字符串
• gen_kwargs: 结构化数据，包含以下字段：
  • do_sample: 数据类型为布尔值
  • max_new_tokens: 数据类型为int64
  • pad_token_id: 数据类型为int64
  • top_k: 数据类型为int64
  • top_p: 数据类型为float64
• reward_1: 数据类型为float64
• reward_2: 数据类型为float64
• n_samples: 数据类型为int64
• reject_select: 数据类型为字符串
• prompt: 数据类型为字符串
• chosen: 数据类型为字符串
• rejected: 数据类型为字符串
• index: 数据类型为int64
• filtered_epoch: 数据类型为int64
• gen_reward: 数据类型为float64
• gen_response: 数据类型为字符串

数据集分割

• epoch_0 至 epoch_29:
  • 每个分割的示例数量均为18929
  • 每个分割的字节数在43586042至44226190之间

数据集大小

• 下载大小: 698623999字节
• 数据集大小: 1325798768字节

数据文件配置

• 每个分割对应的数据文件路径格式为alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_{n}-*，其中n为0至29。