lihaoxin2020/ki-llama3.1-instruct-synthetic_1_stem_only-sft-temp0.6-on-mmlu_pro-0shot_cot-scillm-f66c18ca07

---
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: 4057824
num_examples: 200
download_size: 3963281
dataset_size: 4057824
- 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: 6162892
num_examples: 200
download_size: 6047171
dataset_size: 6162892
- 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: 4440929
num_examples: 200
download_size: 4351721
dataset_size: 4440929
- 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: 9706168
num_examples: 200
download_size: 9570776
dataset_size: 9706168
- 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: 3232891
num_examples: 200
download_size: 3139366
dataset_size: 3232891
- 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: 6021434
num_examples: 200
download_size: 5927153
dataset_size: 6021434
- 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: 7495690
num_examples: 200
download_size: 7389136
dataset_size: 7495690
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-*
---