Mitsuki-Sakamoto/alpaca_farm-deberta-re-pref-64-fil_self_160m_bo16_2_mix_50_kl_0.1_prm_70m_thr_0.0_seed_1_tp_0.7

--- 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: index dtype: int64 - name: prompt dtype: string - name: chosen dtype: string - name: rejected dtype: string - name: filtered_epoch dtype: int64 - name: gen_reward dtype: float64 - name: gen_response dtype: string splits: - name: epoch_0 num_bytes: 43643743 num_examples: 18928 - name: epoch_1 num_bytes: 44177165 num_examples: 18928 - name: epoch_2 num_bytes: 44246509 num_examples: 18928 - name: epoch_3 num_bytes: 44284198 num_examples: 18928 - name: epoch_4 num_bytes: 44299861 num_examples: 18928 - name: epoch_5 num_bytes: 44298633 num_examples: 18928 - name: epoch_6 num_bytes: 44290474 num_examples: 18928 - name: epoch_7 num_bytes: 44285619 num_examples: 18928 - name: epoch_8 num_bytes: 44283669 num_examples: 18928 - name: epoch_9 num_bytes: 44278889 num_examples: 18928 - name: epoch_10 num_bytes: 44277997 num_examples: 18928 - name: epoch_11 num_bytes: 44275995 num_examples: 18928 - name: epoch_12 num_bytes: 44278688 num_examples: 18928 - name: epoch_13 num_bytes: 44277686 num_examples: 18928 - name: epoch_14 num_bytes: 44277063 num_examples: 18928 - name: epoch_15 num_bytes: 44276355 num_examples: 18928 - name: epoch_16 num_bytes: 44275987 num_examples: 18928 - name: epoch_17 num_bytes: 44275029 num_examples: 18928 - name: epoch_18 num_bytes: 44275802 num_examples: 18928 - name: epoch_19 num_bytes: 44276349 num_examples: 18928 - name: epoch_20 num_bytes: 44276151 num_examples: 18928 - name: epoch_21 num_bytes: 44275292 num_examples: 18928 - name: epoch_22 num_bytes: 44276902 num_examples: 18928 - name: epoch_23 num_bytes: 44276528 num_examples: 18928 - name: epoch_24 num_bytes: 44276548 num_examples: 18928 - name: epoch_25 num_bytes: 44275462 num_examples: 18928 - name: epoch_26 num_bytes: 44275979 num_examples: 18928 - name: epoch_27 num_bytes: 44275327 num_examples: 18928 - name: epoch_28 num_bytes: 44275664 num_examples: 18928 - name: epoch_29 num_bytes: 44276230 num_examples: 18928 download_size: 689594562 dataset_size: 1327615794 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-* ---数据集信息： 配置名称：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1 特征： - 名称：instruction，数据类型：字符串 - 名称：input，数据类型：字符串 - 名称：output，数据类型：字符串 - 名称：preference，数据类型：64位整数 - 名称：output_1，数据类型：字符串 - 名称：output_2，数据类型：字符串 - 名称：reward_model_prompt_format，数据类型：字符串 - 名称：gen_prompt_format，数据类型：字符串 - 名称：gen_kwargs，数据类型：结构体，包含字段： - 名称：do_sample，数据类型：布尔值 - 名称：max_new_tokens，数据类型：64位整数 - 名称：pad_token_id，数据类型：64位整数 - 名称：top_k，数据类型：64位整数 - 名称：top_p，数据类型：64位浮点数 - 名称：reward_1，数据类型：64位浮点数 - 名称：reward_2，数据类型：64位浮点数 - 名称：n_samples，数据类型：64位整数 - 名称：reject_select，数据类型：字符串 - 名称：index，数据类型：64位整数 - 名称：prompt，数据类型：字符串 - 名称：chosen，数据类型：字符串 - 名称：rejected，数据类型：字符串 - 名称：filtered_epoch，数据类型：64位整数 - 名称：gen_reward，数据类型：64位浮点数 - 名称：gen_response，数据类型：字符串 数据划分： - 划分名：epoch_0，字节大小：43643743，样本数：18928 - 划分名：epoch_1，字节大小：44177165，样本数：18928 - 划分名：epoch_2，字节大小：44246509，样本数：18928 - 划分名：epoch_3，字节大小：44284198，样本数：18928 - 划分名：epoch_4，字节大小：44299861，样本数：18928 - 划分名：epoch_5，字节大小：44298633，样本数：18928 - 划分名：epoch_6，字节大小：44290474，样本数：18928 - 划分名：epoch_7，字节大小：44285619，样本数：18928 - 划分名：epoch_8，字节大小：44283669，样本数：18928 - 划分名：epoch_9，字节大小：44278889，样本数：18928 - 划分名：epoch_10，字节大小：44277997，样本数：18928 - 划分名：epoch_11，字节大小：44275995，样本数：18928 - 划分名：epoch_12，字节大小：44278688，样本数：18928 - 划分名：epoch_13，字节大小：44277686，样本数：18928 - 划分名：epoch_14，字节大小：44277063，样本数：18928 - 划分名：epoch_15，字节大小：44276355，样本数：18928 - 划分名：epoch_16，字节大小：44275987，样本数：18928 - 划分名：epoch_17，字节大小：44275029，样本数：18928 - 划分名：epoch_18，字节大小：44275802，样本数：18928 - 划分名：epoch_19，字节大小：44276349，样本数：18928 - 划分名：epoch_20，字节大小：44276151，样本数：18928 - 划分名：epoch_21，字节大小：44275292，样本数：18928 - 划分名：epoch_22，字节大小：44276902，样本数：18928 - 划分名：epoch_23，字节大小：44276528，样本数：18928 - 划分名：epoch_24，字节大小：44276548，样本数：18928 - 划分名：epoch_25，字节大小：44275462，样本数：18928 - 划分名：epoch_26，字节大小：44275979，样本数：18928 - 划分名：epoch_27，字节大小：44275327，样本数：18928 - 划分名：epoch_28，字节大小：44275664，样本数：18928 - 划分名：epoch_29，字节大小：44276230，样本数：18928 下载总大小：689594562 字节 数据集总大小：1327615794 字节 配置项： - 配置名称：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1 数据文件列表： - 划分：epoch_0，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_0-* - 划分：epoch_1，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_1-* - 划分：epoch_2，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_2-* - 划分：epoch_3，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_3-* - 划分：epoch_4，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_4-* - 划分：epoch_5，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_5-* - 划分：epoch_6，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_6-* - 划分：epoch_7，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_7-* - 划分：epoch_8，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_8-* - 划分：epoch_9，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_9-* - 划分：epoch_10，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_10-* - 划分：epoch_11，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_11-* - 划分：epoch_12，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_12-* - 划分：epoch_13，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_13-* - 划分：epoch_14，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_14-* - 划分：epoch_15，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_15-* - 划分：epoch_16，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_16-* - 划分：epoch_17，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_17-* - 划分：epoch_18，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_18-* - 划分：epoch_19，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_19-* - 划分：epoch_20，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_20-* - 划分：epoch_21，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_21-* - 划分：epoch_22，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_22-* - 划分：epoch_23，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_23-* - 划分：epoch_24，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_24-* - 划分：epoch_25，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_25-* - 划分：epoch_26，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_26-* - 划分：epoch_27，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_27-* - 划分：epoch_28，路径：alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_28-* - 划分：epoch_29，路径：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

配置名称

• alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1

特征

• instruction: 字符串
• input: 字符串
• output: 字符串
• preference: 整数
• output_1: 字符串
• output_2: 字符串
• reward_model_prompt_format: 字符串
• gen_prompt_format: 字符串
• gen_kwargs: 结构体
  • do_sample: 布尔值
  • max_new_tokens: 整数
  • pad_token_id: 整数
  • top_k: 整数
  • top_p: 浮点数
• reward_1: 浮点数
• reward_2: 浮点数
• n_samples: 整数
• reject_select: 字符串
• index: 整数
• prompt: 字符串
• chosen: 字符串
• rejected: 字符串
• filtered_epoch: 整数
• gen_reward: 浮点数
• gen_response: 字符串

数据分割

• epoch_0: 43643743 字节, 18928 样本
• epoch_1: 44177165 字节, 18928 样本
• epoch_2: 44246509 字节, 18928 样本
• epoch_3: 44284198 字节, 18928 样本
• epoch_4: 44299861 字节, 18928 样本
• epoch_5: 44298633 字节, 18928 样本
• epoch_6: 44290474 字节, 18928 样本
• epoch_7: 44285619 字节, 18928 样本
• epoch_8: 44283669 字节, 18928 样本
• epoch_9: 44278889 字节, 18928 样本
• epoch_10: 44277997 字节, 18928 样本
• epoch_11: 44275995 字节, 18928 样本
• epoch_12: 44278688 字节, 18928 样本
• epoch_13: 44277686 字节, 18928 样本
• epoch_14: 44277063 字节, 18928 样本
• epoch_15: 44276355 字节, 18928 样本
• epoch_16: 44275987 字节, 18928 样本
• epoch_17: 44275029 字节, 18928 样本
• epoch_18: 44275802 字节, 18928 样本
• epoch_19: 44276349 字节, 18928 样本
• epoch_20: 44276151 字节, 18928 样本
• epoch_21: 44275292 字节, 18928 样本
• epoch_22: 44276902 字节, 18928 样本
• epoch_23: 44276528 字节, 18928 样本
• epoch_24: 44276548 字节, 18928 样本
• epoch_25: 44275462 字节, 18928 样本
• epoch_26: 44275979 字节, 18928 样本
• epoch_27: 44275327 字节, 18928 样本
• epoch_28: 44275664 字节, 18928 样本
• epoch_29: 44276230 字节, 18928 样本

数据文件

• epoch_0: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_0-*
• epoch_1: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_1-*
• epoch_2: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_2-*
• epoch_3: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_3-*
• epoch_4: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_4-*
• epoch_5: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_5-*
• epoch_6: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_6-*
• epoch_7: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_7-*
• epoch_8: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_8-*
• epoch_9: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_9-*
• epoch_10: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_10-*
• epoch_11: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_11-*
• epoch_12: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_12-*
• epoch_13: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_13-*
• epoch_14: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_14-*
• epoch_15: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_15-*
• epoch_16: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_16-*
• epoch_17: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_17-*
• epoch_18: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_18-*
• epoch_19: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_19-*
• epoch_20: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_20-*
• epoch_21: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_21-*
• epoch_22: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_22-*
• epoch_23: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_23-*
• epoch_24: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_24-*
• epoch_25: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_25-*
• epoch_26: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_26-*
• epoch_27: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_27-*
• epoch_28: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_28-*
• epoch_29: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_29-*

数据集大小

• 下载大小: 689594562 字节
• 数据集大小: 1327615794 字节