Mitsuki-Sakamoto/alpaca_farm-deberta-re-pref-64-_fil_self_160m_bo16_2_mix_50_kl_0.1_prm_160m_thr_1.0_seed_2

--- 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: 43779189 num_examples: 18928 - name: epoch_1 num_bytes: 44389394 num_examples: 18928 - name: epoch_2 num_bytes: 44452838 num_examples: 18928 - name: epoch_3 num_bytes: 44504767 num_examples: 18928 - name: epoch_4 num_bytes: 44525045 num_examples: 18928 - name: epoch_5 num_bytes: 44512817 num_examples: 18928 - name: epoch_6 num_bytes: 44504063 num_examples: 18928 - name: epoch_7 num_bytes: 44468006 num_examples: 18928 - name: epoch_8 num_bytes: 44457766 num_examples: 18928 - name: epoch_9 num_bytes: 44452281 num_examples: 18928 - name: epoch_10 num_bytes: 44441633 num_examples: 18928 - name: epoch_11 num_bytes: 44440113 num_examples: 18928 - name: epoch_12 num_bytes: 44438738 num_examples: 18928 - name: epoch_13 num_bytes: 44437694 num_examples: 18928 - name: epoch_14 num_bytes: 44438979 num_examples: 18928 - name: epoch_15 num_bytes: 44434772 num_examples: 18928 - name: epoch_16 num_bytes: 44431885 num_examples: 18928 - name: epoch_17 num_bytes: 44430771 num_examples: 18928 - name: epoch_18 num_bytes: 44430902 num_examples: 18928 - name: epoch_19 num_bytes: 44429917 num_examples: 18928 - name: epoch_20 num_bytes: 44430629 num_examples: 18928 - name: epoch_21 num_bytes: 44429778 num_examples: 18928 - name: epoch_22 num_bytes: 44429225 num_examples: 18928 - name: epoch_23 num_bytes: 44432672 num_examples: 18928 - name: epoch_24 num_bytes: 44429439 num_examples: 18928 - name: epoch_25 num_bytes: 44429477 num_examples: 18928 - name: epoch_26 num_bytes: 44429378 num_examples: 18928 - name: epoch_27 num_bytes: 44429813 num_examples: 18928 - name: epoch_28 num_bytes: 44426534 num_examples: 18928 - name: epoch_29 num_bytes: 44428539 num_examples: 18928 download_size: 700085000 dataset_size: 1332697054 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。
• index: 数据类型为int64。
• 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。
• 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18928。
  • 每个分割的存储大小在43779189字节至44525045字节之间。

数据集大小

• 下载大小: 700085000字节
• 数据集大小: 1332697054字节