lihaoxin2020/ki-qwen-instruct-synthetic_1_qwen_math_only-sft-on-mmlu_pro-0shot_cot-scillm-914848b0f2

---
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: 3400919
num_examples: 200
download_size: 3299032
dataset_size: 3400919
- 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: 5274026
num_examples: 200
download_size: 5152922
dataset_size: 5274026
- 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: 4285931
num_examples: 200
download_size: 4181815
dataset_size: 4285931
- 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: 8334129
num_examples: 200
download_size: 8186903
dataset_size: 8334129
- 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: 3768026
num_examples: 200
download_size: 3662559
dataset_size: 3768026
- 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: 3559686
num_examples: 200
download_size: 3465625
dataset_size: 3559686
- 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: 5720930
num_examples: 200
download_size: 5603845
dataset_size: 5720930
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-*
---