TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3arg_OLMO_RLONLY-RL

---
dataset_info:
features:
- name: question
dtype: string
- name: answer
dtype: string
- name: task_config
dtype: string
- name: task_source
dtype: string
- name: prompt
list:
- name: content
dtype: string
- name: role
dtype: string
- name: model_responses
list: 'null'
- name: model_responses__eval_is_correct
list: 'null'
- name: all_other_columns
dtype: string
- name: original_split
dtype: string
- name: metadata
dtype: string
- name: model_responses__best_of_n_atags
list: string
- name: model_responses__best_of_n_atags__finish_reason_length_flags
list: bool
- name: model_responses__best_of_n_atags__length_partial_responses
list: string
- name: prompt__best_of_n_atags__metadata
dtype: string
- name: model_responses__best_of_n_atags__metadata
dtype: string
- name: model_responses__best_of_n_atags__eval_is_correct
list: bool
- name: model_responses__best_of_n_atags__eval_extracted_answers
list: string
- name: model_responses__best_of_n_atags__eval_extraction_metadata
dtype: string
- name: model_responses__best_of_n_atags__eval_evaluation_metadata
dtype: string
- name: model_responses__best_of_n_atags__internal_answers__eval_is_correct
list:
list: bool
- name: model_responses__best_of_n_atags__internal_answers__eval_extracted_answers
list:
list: string
- name: model_responses__best_of_n_atags__internal_answers__eval_extraction_metadata
dtype: string
- name: model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
dtype: string
- name: model_responses__best_of_n_atags__metrics
struct:
- name: flips_by
list: int64
- name: flips_total
dtype: int64
- name: num_correct
dtype: int64
- name: pass_at_n
dtype: int64
- name: percent_correct
dtype: float64
- name: total_responses
dtype: int64
- name: eval_date
dtype: string
- name: choices
dtype: string
- name: answer_index
dtype: int64
- name: answer_key
dtype: string
- name: id
dtype: string
- name: difficulty
dtype: string
- name: domain
dtype: string
- name: evaluation_type
dtype: string
- name: expected_answer_format
dtype: string
- name: original_answer
dtype: string
- name: source
dtype: string
- name: task_type
dtype: string
- name: variant
dtype: string
- name: acronym
dtype: string
- name: formed_acronym
dtype: string
- name: word_count
dtype: int64
- name: words
list: string
- name: length
dtype: int64
- name: letters
dtype: string
splits:
- name: train
num_bytes: 289735822
num_examples: 11481
download_size: 43862784
dataset_size: 289735822
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---