Mitsuki-Sakamoto/alpaca_farm-deberta-re-pref-64-fil_self_160m_bo16_2_mix_50_kl_0.1_prm_70m_thr_0.0_seed_3_t_0.5

--- 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: 43662007 num_examples: 18928 - name: epoch_1 num_bytes: 44132843 num_examples: 18928 - name: epoch_2 num_bytes: 44207080 num_examples: 18928 - name: epoch_3 num_bytes: 44255371 num_examples: 18928 - name: epoch_4 num_bytes: 44273197 num_examples: 18928 - name: epoch_5 num_bytes: 44280253 num_examples: 18928 - name: epoch_6 num_bytes: 44277798 num_examples: 18928 - name: epoch_7 num_bytes: 44278037 num_examples: 18928 - name: epoch_8 num_bytes: 44273381 num_examples: 18928 - name: epoch_9 num_bytes: 44271632 num_examples: 18928 - name: epoch_10 num_bytes: 44270921 num_examples: 18928 - name: epoch_11 num_bytes: 44270373 num_examples: 18928 - name: epoch_12 num_bytes: 44268355 num_examples: 18928 - name: epoch_13 num_bytes: 44269373 num_examples: 18928 - name: epoch_14 num_bytes: 44269604 num_examples: 18928 - name: epoch_15 num_bytes: 44270869 num_examples: 18928 - name: epoch_16 num_bytes: 44271077 num_examples: 18928 - name: epoch_17 num_bytes: 44269424 num_examples: 18928 - name: epoch_18 num_bytes: 44271250 num_examples: 18928 - name: epoch_19 num_bytes: 44269801 num_examples: 18928 - name: epoch_20 num_bytes: 44270673 num_examples: 18928 - name: epoch_21 num_bytes: 44269581 num_examples: 18928 - name: epoch_22 num_bytes: 44271005 num_examples: 18928 - name: epoch_23 num_bytes: 44270821 num_examples: 18928 - name: epoch_24 num_bytes: 44270189 num_examples: 18928 - name: epoch_25 num_bytes: 44269261 num_examples: 18928 - name: epoch_26 num_bytes: 44270226 num_examples: 18928 - name: epoch_27 num_bytes: 44271066 num_examples: 18928 - name: epoch_28 num_bytes: 44271734 num_examples: 18928 - name: epoch_29 num_bytes: 44271600 num_examples: 18928 download_size: 685464577 dataset_size: 1327318802 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 结构体: - 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: - 划分名称: epoch_0 字节数: 43662007 样本数量: 18928 - 划分名称: epoch_1 字节数: 44132843 样本数量: 18928 - 划分名称: epoch_2 字节数: 44207080 样本数量: 18928 - 划分名称: epoch_3 字节数: 44255371 样本数量: 18928 - 划分名称: epoch_4 字节数: 44273197 样本数量: 18928 - 划分名称: epoch_5 字节数: 44280253 样本数量: 18928 - 划分名称: epoch_6 字节数: 44277798 样本数量: 18928 - 划分名称: epoch_7 字节数: 44278037 样本数量: 18928 - 划分名称: epoch_8 字节数: 44273381 样本数量: 18928 - 划分名称: epoch_9 字节数: 44271632 样本数量: 18928 - 划分名称: epoch_10 字节数: 44270921 样本数量: 18928 - 划分名称: epoch_11 字节数: 44270373 样本数量: 18928 - 划分名称: epoch_12 字节数: 44268355 样本数量: 18928 - 划分名称: epoch_13 字节数: 44269373 样本数量: 18928 - 划分名称: epoch_14 字节数: 44269604 样本数量: 18928 - 划分名称: epoch_15 字节数: 44270869 样本数量: 18928 - 划分名称: epoch_16 字节数: 44271077 样本数量: 18928 - 划分名称: epoch_17 字节数: 44269424 样本数量: 18928 - 划分名称: epoch_18 字节数: 44271250 样本数量: 18928 - 划分名称: epoch_19 字节数: 44269801 样本数量: 18928 - 划分名称: epoch_20 字节数: 44270673 样本数量: 18928 - 划分名称: epoch_21 字节数: 44269581 样本数量: 18928 - 划分名称: epoch_22 字节数: 44271005 样本数量: 18928 - 划分名称: epoch_23 字节数: 44270821 样本数量: 18928 - 划分名称: epoch_24 字节数: 44270189 样本数量: 18928 - 划分名称: epoch_25 字节数: 44269261 样本数量: 18928 - 划分名称: epoch_26 字节数: 44270226 样本数量: 18928 - 划分名称: epoch_27 字节数: 44271066 样本数量: 18928 - 划分名称: epoch_28 字节数: 44271734 样本数量: 18928 - 划分名称: epoch_29 字节数: 44271600 样本数量: 18928 下载大小: 685464577 数据集总大小: 1327318802 配置项: - 配置名称: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1 数据文件: - 数据划分: epoch_0 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_0-* - 数据划分: epoch_1 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_1-* - 数据划分: epoch_2 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_2-* - 数据划分: epoch_3 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_3-* - 数据划分: epoch_4 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_4-* - 数据划分: epoch_5 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_5-* - 数据划分: epoch_6 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_6-* - 数据划分: epoch_7 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_7-* - 数据划分: epoch_8 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_8-* - 数据划分: epoch_9 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_9-* - 数据划分: epoch_10 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_10-* - 数据划分: epoch_11 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_11-* - 数据划分: epoch_12 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_12-* - 数据划分: epoch_13 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_13-* - 数据划分: epoch_14 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_14-* - 数据划分: epoch_15 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_15-* - 数据划分: epoch_16 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_16-* - 数据划分: epoch_17 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_17-* - 数据划分: epoch_18 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_18-* - 数据划分: epoch_19 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_19-* - 数据划分: epoch_20 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_20-* - 数据划分: epoch_21 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_21-* - 数据划分: epoch_22 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_22-* - 数据划分: epoch_23 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_23-* - 数据划分: epoch_24 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_24-* - 数据划分: epoch_25 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_25-* - 数据划分: epoch_26 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_26-* - 数据划分: epoch_27 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_27-* - 数据划分: epoch_28 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/epoch_28-* - 数据划分: 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

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：字符串类型
• input：字符串类型
• output：字符串类型
• preference：整数类型（int64）
• output_1：字符串类型
• output_2：字符串类型
• reward_model_prompt_format：字符串类型
• gen_prompt_format：字符串类型
• gen_kwargs：结构体类型，包含以下字段：
  • do_sample：布尔类型
  • max_new_tokens：整数类型（int64）
  • pad_token_id：整数类型（int64）
  • top_k：整数类型（int64）
  • top_p：浮点类型（float64）
• reward_1：浮点类型（float64）
• reward_2：浮点类型（float64）
• n_samples：整数类型（int64）
• reject_select：字符串类型
• index：整数类型（int64）
• prompt：字符串类型
• chosen：字符串类型
• rejected：字符串类型
• filtered_epoch：整数类型（int64）
• gen_reward：浮点类型（float64）
• gen_response：字符串类型

数据集分割

• epoch_0 至 epoch_29：每个分割包含18928个示例，大小在43662007至44280253字节之间。

数据集大小

• 下载大小：685464577字节
• 数据集大小：1327318802字节