andrewsiah/rewarded-FsfairX-LLaMA3-RM-v0.1_s125_e250
收藏Hugging Face2024-05-23 更新2024-06-12 收录
下载链接:
https://hf-mirror.com/datasets/andrewsiah/rewarded-FsfairX-LLaMA3-RM-v0.1_s125_e250
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
features:
- name: reward_1
dtype: float64
- name: reward_2
dtype: float64
- name: reward_3
dtype: float64
- name: reward_4
dtype: float64
- name: reward_5
dtype: float64
- name: reward_6
dtype: float64
- name: reward_7
dtype: float64
- name: reward_8
dtype: float64
- name: reward_9
dtype: float64
- name: reward_10
dtype: float64
- name: reward_11
dtype: float64
- name: reward_12
dtype: float64
- name: reward_13
dtype: float64
- name: reward_14
dtype: float64
- name: reward_15
dtype: float64
- name: reward_16
dtype: float64
- name: reward_17
dtype: float64
- name: reward_18
dtype: float64
- name: reward_19
dtype: float64
- name: reward_20
dtype: float64
- name: reward_21
dtype: float64
- name: reward_22
dtype: float64
- name: reward_23
dtype: float64
- name: reward_24
dtype: float64
- name: reward_25
dtype: float64
- name: reward_26
dtype: float64
- name: reward_27
dtype: float64
- name: reward_28
dtype: float64
- name: reward_29
dtype: float64
- name: reward_30
dtype: float64
- name: reward_31
dtype: float64
- name: reward_32
dtype: float64
- name: reward_33
dtype: float64
- name: reward_34
dtype: float64
- name: reward_35
dtype: float64
- name: reward_36
dtype: float64
- name: reward_37
dtype: float64
- name: reward_38
dtype: float64
- name: reward_39
dtype: float64
- name: reward_40
dtype: float64
- name: reward_41
dtype: float64
- name: reward_42
dtype: float64
- name: reward_43
dtype: float64
- name: reward_44
dtype: float64
- name: reward_45
dtype: float64
- name: reward_46
dtype: float64
- name: reward_47
dtype: float64
- name: reward_48
dtype: float64
- name: reward_49
dtype: float64
- name: reward_50
dtype: float64
- name: reward_51
dtype: float64
- name: reward_52
dtype: float64
- name: reward_53
dtype: float64
- name: reward_54
dtype: float64
- name: reward_55
dtype: float64
- name: reward_56
dtype: float64
- name: reward_57
dtype: float64
- name: reward_58
dtype: float64
- name: reward_59
dtype: float64
- name: reward_60
dtype: float64
- name: reward_61
dtype: float64
- name: reward_62
dtype: float64
- name: reward_63
dtype: float64
- name: reward_64
dtype: float64
- name: reward_65
dtype: float64
- name: reward_66
dtype: float64
- name: reward_67
dtype: float64
- name: reward_68
dtype: float64
- name: reward_69
dtype: float64
- name: reward_70
dtype: float64
- name: reward_71
dtype: float64
- name: reward_72
dtype: float64
- name: reward_73
dtype: float64
- name: reward_74
dtype: float64
- name: reward_75
dtype: float64
- name: reward_76
dtype: float64
- name: reward_77
dtype: float64
- name: reward_78
dtype: float64
- name: reward_79
dtype: float64
- name: reward_80
dtype: float64
- name: reward_81
dtype: float64
- name: reward_82
dtype: float64
- name: reward_83
dtype: float64
- name: reward_84
dtype: float64
- name: reward_85
dtype: float64
- name: reward_86
dtype: float64
- name: reward_87
dtype: float64
- name: reward_88
dtype: float64
- name: reward_89
dtype: float64
- name: reward_90
dtype: float64
- name: reward_91
dtype: float64
- name: reward_92
dtype: float64
- name: reward_93
dtype: float64
- name: reward_94
dtype: float64
- name: reward_95
dtype: float64
- name: reward_96
dtype: float64
- name: reward_97
dtype: float64
- name: reward_98
dtype: float64
- name: reward_99
dtype: float64
- name: reward_100
dtype: float64
- name: prompt
dtype: string
- name: subset
dtype: string
- name: rewardbench_chosen
dtype: string
- name: rewardbench_chosen_model
dtype: string
- name: rewardbench_rejected
dtype: string
- name: rewardbench_rejected_model
dtype: string
- name: response_1
dtype: string
- name: response_1_model
dtype: string
- name: response_2
dtype: string
- name: response_2_model
dtype: string
- name: response_3
dtype: string
- name: response_3_model
dtype: string
- name: response_4
dtype: string
- name: response_4_model
dtype: string
- name: response_5
dtype: string
- name: response_5_model
dtype: string
- name: response_6
dtype: string
- name: response_6_model
dtype: string
- name: response_7
dtype: string
- name: response_7_model
dtype: string
- name: response_8
dtype: string
- name: response_8_model
dtype: string
- name: response_9
dtype: string
- name: response_9_model
dtype: string
- name: response_10
dtype: string
- name: response_10_model
dtype: string
- name: response_11
dtype: string
- name: response_11_model
dtype: string
- name: response_12
dtype: string
- name: response_12_model
dtype: string
- name: response_13
dtype: string
- name: response_13_model
dtype: string
- name: response_14
dtype: string
- name: response_14_model
dtype: string
- name: response_15
dtype: string
- name: response_15_model
dtype: string
- name: response_16
dtype: string
- name: response_16_model
dtype: string
- name: response_17
dtype: string
- name: response_17_model
dtype: string
- name: response_18
dtype: string
- name: response_18_model
dtype: string
- name: response_19
dtype: string
- name: response_19_model
dtype: string
- name: response_20
dtype: string
- name: response_20_model
dtype: string
- name: response_21
dtype: string
- name: response_21_model
dtype: string
- name: response_22
dtype: string
- name: response_22_model
dtype: string
- name: response_23
dtype: string
- name: response_23_model
dtype: string
- name: response_24
dtype: string
- name: response_24_model
dtype: string
- name: response_25
dtype: string
- name: response_25_model
dtype: string
- name: response_26
dtype: string
- name: response_26_model
dtype: string
- name: response_27
dtype: string
- name: response_27_model
dtype: string
- name: response_28
dtype: string
- name: response_28_model
dtype: string
- name: response_29
dtype: string
- name: response_29_model
dtype: string
- name: response_30
dtype: string
- name: response_30_model
dtype: string
- name: response_31
dtype: string
- name: response_31_model
dtype: string
- name: response_32
dtype: string
- name: response_32_model
dtype: string
- name: response_33
dtype: string
- name: response_33_model
dtype: string
- name: response_34
dtype: string
- name: response_34_model
dtype: string
- name: response_35
dtype: string
- name: response_35_model
dtype: string
- name: response_36
dtype: string
- name: response_36_model
dtype: string
- name: response_37
dtype: string
- name: response_37_model
dtype: string
- name: response_38
dtype: string
- name: response_38_model
dtype: string
- name: response_39
dtype: string
- name: response_39_model
dtype: string
- name: response_40
dtype: string
- name: response_40_model
dtype: string
- name: response_41
dtype: string
- name: response_41_model
dtype: string
- name: response_42
dtype: string
- name: response_42_model
dtype: string
- name: response_43
dtype: string
- name: response_43_model
dtype: string
- name: response_44
dtype: string
- name: response_44_model
dtype: string
- name: response_45
dtype: string
- name: response_45_model
dtype: string
- name: response_46
dtype: string
- name: response_46_model
dtype: string
- name: response_47
dtype: string
- name: response_47_model
dtype: string
- name: response_48
dtype: string
- name: response_48_model
dtype: string
- name: response_49
dtype: string
- name: response_49_model
dtype: string
- name: response_50
dtype: string
- name: response_50_model
dtype: string
- name: response_51
dtype: string
- name: response_51_model
dtype: string
- name: response_52
dtype: string
- name: response_52_model
dtype: string
- name: response_53
dtype: string
- name: response_53_model
dtype: string
- name: response_54
dtype: string
- name: response_54_model
dtype: string
- name: response_55
dtype: string
- name: response_55_model
dtype: string
- name: response_56
dtype: string
- name: response_56_model
dtype: string
- name: response_57
dtype: string
- name: response_57_model
dtype: string
- name: response_58
dtype: string
- name: response_58_model
dtype: string
- name: response_59
dtype: string
- name: response_59_model
dtype: string
- name: response_60
dtype: string
- name: response_60_model
dtype: string
- name: response_61
dtype: string
- name: response_61_model
dtype: string
- name: response_62
dtype: string
- name: response_62_model
dtype: string
- name: response_63
dtype: string
- name: response_63_model
dtype: string
- name: response_64
dtype: string
- name: response_64_model
dtype: string
- name: response_65
dtype: string
- name: response_65_model
dtype: string
- name: response_66
dtype: string
- name: response_66_model
dtype: string
- name: response_67
dtype: string
- name: response_67_model
dtype: string
- name: response_68
dtype: string
- name: response_68_model
dtype: string
- name: response_69
dtype: string
- name: response_69_model
dtype: string
- name: response_70
dtype: string
- name: response_70_model
dtype: string
- name: response_71
dtype: string
- name: response_71_model
dtype: string
- name: response_72
dtype: string
- name: response_72_model
dtype: string
- name: response_73
dtype: string
- name: response_73_model
dtype: string
- name: response_74
dtype: string
- name: response_74_model
dtype: string
- name: response_75
dtype: string
- name: response_75_model
dtype: string
- name: response_76
dtype: string
- name: response_76_model
dtype: string
- name: response_77
dtype: string
- name: response_77_model
dtype: string
- name: response_78
dtype: string
- name: response_78_model
dtype: string
- name: response_79
dtype: string
- name: response_79_model
dtype: string
- name: response_80
dtype: string
- name: response_80_model
dtype: string
- name: response_81
dtype: string
- name: response_81_model
dtype: string
- name: response_82
dtype: string
- name: response_82_model
dtype: string
- name: response_83
dtype: string
- name: response_83_model
dtype: string
- name: response_84
dtype: string
- name: response_84_model
dtype: string
- name: response_85
dtype: string
- name: response_85_model
dtype: string
- name: response_86
dtype: string
- name: response_86_model
dtype: string
- name: response_87
dtype: string
- name: response_87_model
dtype: string
- name: response_88
dtype: string
- name: response_88_model
dtype: string
- name: response_89
dtype: string
- name: response_89_model
dtype: string
- name: response_90
dtype: string
- name: response_90_model
dtype: string
- name: response_91
dtype: string
- name: response_91_model
dtype: string
- name: response_92
dtype: string
- name: response_92_model
dtype: string
- name: response_93
dtype: string
- name: response_93_model
dtype: string
- name: response_94
dtype: string
- name: response_94_model
dtype: string
- name: response_95
dtype: string
- name: response_95_model
dtype: string
- name: response_96
dtype: string
- name: response_96_model
dtype: string
- name: response_97
dtype: string
- name: response_97_model
dtype: string
- name: response_98
dtype: string
- name: response_98_model
dtype: string
- name: response_99
dtype: string
- name: response_99_model
dtype: string
- name: response_100
dtype: string
- name: response_100_model
dtype: string
- name: rformatted_prompt_response_1
dtype: string
- name: rformatted_prompt_response_2
dtype: string
- name: rformatted_prompt_response_3
dtype: string
- name: rformatted_prompt_response_4
dtype: string
- name: rformatted_prompt_response_5
dtype: string
- name: rformatted_prompt_response_6
dtype: string
- name: rformatted_prompt_response_7
dtype: string
- name: rformatted_prompt_response_8
dtype: string
- name: rformatted_prompt_response_9
dtype: string
- name: rformatted_prompt_response_10
dtype: string
- name: rformatted_prompt_response_11
dtype: string
- name: rformatted_prompt_response_12
dtype: string
- name: rformatted_prompt_response_13
dtype: string
- name: rformatted_prompt_response_14
dtype: string
- name: rformatted_prompt_response_15
dtype: string
- name: rformatted_prompt_response_16
dtype: string
- name: rformatted_prompt_response_17
dtype: string
- name: rformatted_prompt_response_18
dtype: string
- name: rformatted_prompt_response_19
dtype: string
- name: rformatted_prompt_response_20
dtype: string
- name: rformatted_prompt_response_21
dtype: string
- name: rformatted_prompt_response_22
dtype: string
- name: rformatted_prompt_response_23
dtype: string
- name: rformatted_prompt_response_24
dtype: string
- name: rformatted_prompt_response_25
dtype: string
- name: rformatted_prompt_response_26
dtype: string
- name: rformatted_prompt_response_27
dtype: string
- name: rformatted_prompt_response_28
dtype: string
- name: rformatted_prompt_response_29
dtype: string
- name: rformatted_prompt_response_30
dtype: string
- name: rformatted_prompt_response_31
dtype: string
- name: rformatted_prompt_response_32
dtype: string
- name: rformatted_prompt_response_33
dtype: string
- name: rformatted_prompt_response_34
dtype: string
- name: rformatted_prompt_response_35
dtype: string
- name: rformatted_prompt_response_36
dtype: string
- name: rformatted_prompt_response_37
dtype: string
- name: rformatted_prompt_response_38
dtype: string
- name: rformatted_prompt_response_39
dtype: string
- name: rformatted_prompt_response_40
dtype: string
- name: rformatted_prompt_response_41
dtype: string
- name: rformatted_prompt_response_42
dtype: string
- name: rformatted_prompt_response_43
dtype: string
- name: rformatted_prompt_response_44
dtype: string
- name: rformatted_prompt_response_45
dtype: string
- name: rformatted_prompt_response_46
dtype: string
- name: rformatted_prompt_response_47
dtype: string
- name: rformatted_prompt_response_48
dtype: string
- name: rformatted_prompt_response_49
dtype: string
- name: rformatted_prompt_response_50
dtype: string
- name: rformatted_prompt_response_51
dtype: string
- name: rformatted_prompt_response_52
dtype: string
- name: rformatted_prompt_response_53
dtype: string
- name: rformatted_prompt_response_54
dtype: string
- name: rformatted_prompt_response_55
dtype: string
- name: rformatted_prompt_response_56
dtype: string
- name: rformatted_prompt_response_57
dtype: string
- name: rformatted_prompt_response_58
dtype: string
- name: rformatted_prompt_response_59
dtype: string
- name: rformatted_prompt_response_60
dtype: string
- name: rformatted_prompt_response_61
dtype: string
- name: rformatted_prompt_response_62
dtype: string
- name: rformatted_prompt_response_63
dtype: string
- name: rformatted_prompt_response_64
dtype: string
- name: rformatted_prompt_response_65
dtype: string
- name: rformatted_prompt_response_66
dtype: string
- name: rformatted_prompt_response_67
dtype: string
- name: rformatted_prompt_response_68
dtype: string
- name: rformatted_prompt_response_69
dtype: string
- name: rformatted_prompt_response_70
dtype: string
- name: rformatted_prompt_response_71
dtype: string
- name: rformatted_prompt_response_72
dtype: string
- name: rformatted_prompt_response_73
dtype: string
- name: rformatted_prompt_response_74
dtype: string
- name: rformatted_prompt_response_75
dtype: string
- name: rformatted_prompt_response_76
dtype: string
- name: rformatted_prompt_response_77
dtype: string
- name: rformatted_prompt_response_78
dtype: string
- name: rformatted_prompt_response_79
dtype: string
- name: rformatted_prompt_response_80
dtype: string
- name: rformatted_prompt_response_81
dtype: string
- name: rformatted_prompt_response_82
dtype: string
- name: rformatted_prompt_response_83
dtype: string
- name: rformatted_prompt_response_84
dtype: string
- name: rformatted_prompt_response_85
dtype: string
- name: rformatted_prompt_response_86
dtype: string
- name: rformatted_prompt_response_87
dtype: string
- name: rformatted_prompt_response_88
dtype: string
- name: rformatted_prompt_response_89
dtype: string
- name: rformatted_prompt_response_90
dtype: string
- name: rformatted_prompt_response_91
dtype: string
- name: rformatted_prompt_response_92
dtype: string
- name: rformatted_prompt_response_93
dtype: string
- name: rformatted_prompt_response_94
dtype: string
- name: rformatted_prompt_response_95
dtype: string
- name: rformatted_prompt_response_96
dtype: string
- name: rformatted_prompt_response_97
dtype: string
- name: rformatted_prompt_response_98
dtype: string
- name: rformatted_prompt_response_99
dtype: string
- name: rformatted_prompt_response_100
dtype: string
splits:
- name: train
num_bytes: 38068450
num_examples: 125
download_size: 22534796
dataset_size: 38068450
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
The dataset contains a large number of reward and response fields, each with associated models. The features of the dataset include rewards, prompts, responses, and formatted prompt-response pairs. The datasets splits, including the training split with its size and number of examples, are also detailed. The dataset configuration and data file paths are mentioned in the document.
提供机构:
andrewsiah
原始信息汇总
数据集概述
数据集特征
-
数值特征:
- 包含100个名为
reward_1至reward_100的特征,均为float64类型。
- 包含100个名为
-
字符串特征:
- 包含多个字符串类型的特征,如
prompt,subset,rewardbench_chosen,rewardbench_chosen_model等。 - 包含多个响应相关的特征,如
response_1至response_100及其对应的模型标识response_1_model至response_100_model。 - 包含多个格式化提示响应特征,如
rformatted_prompt_response_1至rformatted_prompt_response_100。
- 包含多个字符串类型的特征,如
数据集分割
- 分割信息:
- 名称:
train - 字节数:38068450
- 示例数:125
- 名称:
数据集大小
- 下载大小:22534796字节
- 数据集大小:38068450字节



