lihaoxin2020/ki-qwen-insturct-synthetic_1-sft-on-mmlu_pro-0shot_cot-scillm-339cb41f45

---
dataset_info:
- config_name: biology
features:
- name: data
list:
- name: content
dtype: string
- name: role
dtype: string
- name: raw_response
struct:
- name: text
dtype: string
- name: raw_text
dtype: string
- name: knowledge_pieces
list: string
- name: doc_id
dtype: int64
- name: native_id
dtype: int64
splits:
- name: train
num_bytes: 3350034
num_examples: 200
download_size: 3245009
dataset_size: 3350034
- config_name: chemistry
features:
- name: data
list:
- name: content
dtype: string
- name: role
dtype: string
- name: raw_response
struct:
- name: text
dtype: string
- name: raw_text
dtype: string
- name: knowledge_pieces
list: string
- name: doc_id
dtype: int64
- name: native_id
dtype: int64
splits:
- name: train
num_bytes: 5545777
num_examples: 199
download_size: 5422250
dataset_size: 5545777
- config_name: computer science
features:
- name: data
list:
- name: content
dtype: string
- name: role
dtype: string
- name: raw_response
struct:
- name: text
dtype: string
- name: raw_text
dtype: string
- name: knowledge_pieces
list: string
- name: doc_id
dtype: int64
- name: native_id
dtype: int64
splits:
- name: train
num_bytes: 3526547
num_examples: 200
download_size: 3428907
dataset_size: 3526547
- config_name: engineering
features:
- name: data
list:
- name: content
dtype: string
- name: role
dtype: string
- name: raw_response
struct:
- name: text
dtype: string
- name: raw_text
dtype: string
- name: knowledge_pieces
list: string
- name: doc_id
dtype: int64
- name: native_id
dtype: int64
splits:
- name: train
num_bytes: 7852937
num_examples: 199
download_size: 7700347
dataset_size: 7852937
- config_name: health
features:
- name: data
list:
- name: content
dtype: string
- name: role
dtype: string
- name: raw_response
struct:
- name: text
dtype: string
- name: raw_text
dtype: string
- name: knowledge_pieces
list: string
- name: doc_id
dtype: int64
- name: native_id
dtype: int64
splits:
- name: train
num_bytes: 3275161
num_examples: 200
download_size: 3169845
dataset_size: 3275161
- config_name: math
features:
- name: data
list:
- name: content
dtype: string
- name: role
dtype: string
- name: raw_response
struct:
- name: text
dtype: string
- name: raw_text
dtype: string
- name: knowledge_pieces
list: string
- name: doc_id
dtype: int64
- name: native_id
dtype: int64
splits:
- name: train
num_bytes: 3174028
num_examples: 200
download_size: 3080356
dataset_size: 3174028
- config_name: physics
features:
- name: data
list:
- name: content
dtype: string
- name: role
dtype: string
- name: raw_response
struct:
- name: text
dtype: string
- name: raw_text
dtype: string
- name: knowledge_pieces
list: string
- name: doc_id
dtype: int64
- name: native_id
dtype: int64
splits:
- name: train
num_bytes: 5133621
num_examples: 200
download_size: 5018940
dataset_size: 5133621
configs:
- config_name: biology
data_files:
- split: train
path: biology/train-*
- config_name: chemistry
data_files:
- split: train
path: chemistry/train-*
- config_name: computer science
data_files:
- split: train
path: computer science/train-*
- config_name: engineering
data_files:
- split: train
path: engineering/train-*
- config_name: health
data_files:
- split: train
path: health/train-*
- config_name: math
data_files:
- split: train
path: math/train-*
- config_name: physics
data_files:
- split: train
path: physics/train-*
---