mehuldamani/classifier-v1-SFT

---
dataset_info:
features:
- name: conversation_hash
dtype: string
- name: model
dtype: string
- name: timestamp
dtype: timestamp[us]
- name: conversation
list:
- name: content
dtype: string
- name: country
dtype: string
- name: created
dtype: int64
- name: hashed_ip
dtype: string
- name: header
struct:
- name: accept-language
dtype: string
- name: user-agent
dtype: string
- name: language
dtype: string
- name: openai_id
dtype: string
- name: redacted
dtype: bool
- name: role
dtype: string
- name: state
dtype: string
- name: system_fingerprint
dtype: string
- name: temperature
dtype: float64
- name: timestamp
dtype: timestamp[us]
- name: token_counter
dtype: int64
- name: top_p
dtype: float64
- name: toxic
dtype: bool
- name: turn_identifier
dtype: int64
- name: usage
dtype: 'null'
- name: turn
dtype: int64
- name: language
dtype: string
- name: openai_moderation
list:
- name: categories
struct:
- name: harassment
dtype: bool
- name: harassment/threatening
dtype: bool
- name: harassment_threatening
dtype: bool
- name: hate
dtype: bool
- name: hate/threatening
dtype: bool
- name: hate_threatening
dtype: bool
- name: illicit
dtype: bool
- name: illicit/violent
dtype: bool
- name: illicit_violent
dtype: bool
- name: self-harm
dtype: bool
- name: self-harm/instructions
dtype: bool
- name: self-harm/intent
dtype: bool
- name: self_harm
dtype: bool
- name: self_harm_instructions
dtype: bool
- name: self_harm_intent
dtype: bool
- name: sexual
dtype: bool
- name: sexual/minors
dtype: bool
- name: sexual_minors
dtype: bool
- name: violence
dtype: bool
- name: violence/graphic
dtype: bool
- name: violence_graphic
dtype: bool
- name: category_applied_input_types
struct:
- name: harassment
list: string
- name: harassment/threatening
list: string
- name: harassment_threatening
list: string
- name: hate
list: string
- name: hate/threatening
list: string
- name: hate_threatening
list: string
- name: illicit
list: string
- name: illicit/violent
list: string
- name: illicit_violent
list: string
- name: self-harm
list: string
- name: self-harm/instructions
list: string
- name: self-harm/intent
list: string
- name: self_harm
list: string
- name: self_harm_instructions
list: string
- name: self_harm_intent
list: string
- name: sexual
list: string
- name: sexual/minors
list: string
- name: sexual_minors
list: string
- name: violence
list: string
- name: violence/graphic
list: string
- name: violence_graphic
list: string
- name: category_scores
struct:
- name: harassment
dtype: float64
- name: harassment/threatening
dtype: float64
- name: harassment_threatening
dtype: float64
- name: hate
dtype: float64
- name: hate/threatening
dtype: float64
- name: hate_threatening
dtype: float64
- name: illicit
dtype: float64
- name: illicit/violent
dtype: float64
- name: illicit_violent
dtype: float64
- name: self-harm
dtype: float64
- name: self-harm/instructions
dtype: float64
- name: self-harm/intent
dtype: float64
- name: self_harm
dtype: float64
- name: self_harm_instructions
dtype: float64
- name: self_harm_intent
dtype: float64
- name: sexual
dtype: float64
- name: sexual/minors
dtype: float64
- name: sexual_minors
dtype: float64
- name: violence
dtype: float64
- name: violence/graphic
dtype: float64
- name: violence_graphic
dtype: float64
- name: flagged
dtype: bool
- name: detoxify_moderation
list:
- name: identity_attack
dtype: float64
- name: insult
dtype: float64
- name: obscene
dtype: float64
- name: severe_toxicity
dtype: float64
- name: sexual_explicit
dtype: float64
- name: threat
dtype: float64
- name: toxicity
dtype: float64
- name: toxic
dtype: bool
- name: redacted
dtype: bool
- name: state
dtype: string
- name: country
dtype: string
- name: hashed_ip
dtype: string
- name: header
struct:
- name: accept-language
dtype: string
- name: user-agent
dtype: string
- name: roles
list: string
- name: label
dtype: int64
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
- name: selected_text
dtype: string
splits:
- name: train
num_bytes: 761315141.0
num_examples: 20000
- name: test
num_bytes: 34978351.0
num_examples: 1000
download_size: 323357042
dataset_size: 796293492.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
---