fernandabufon/redator_v1_openai-gpt-oss-20b_reasoning_low_eval_samples

---
dataset_info:
features:
- name: query_idx
dtype: int64
- name: query
dtype: large_string
- name: answer
dtype: large_string
- name: num_questions
dtype: int64
- name: binary_count
dtype: int64
- name: numeric_count
dtype: int64
- name: structured_count
dtype: int64
- name: textual_count
dtype: int64
- name: binary_correct
dtype: int64
- name: numeric_correct
dtype: int64
- name: structured_correct
dtype: int64
- name: textual_correct
dtype: int64
- name: binary_empty
dtype: int64
- name: numeric_empty
dtype: int64
- name: structured_empty
dtype: int64
- name: textual_empty
dtype: int64
- name: binary_accuracy
dtype: float64
- name: numeric_accuracy
dtype: float64
- name: structured_accuracy
dtype: float64
- name: textual_accuracy
dtype: float64
- name: accuracy
dtype: float64
- name: textual_rouge1_mean
dtype: float64
- name: textual_rouge2_mean
dtype: float64
- name: textual_rougeL_mean
dtype: float64
- name: textual_bleu_mean
dtype: float64
- name: model
dtype: large_string
- name: reasoning_effort
dtype: large_string
splits:
- name: train
num_bytes: 72143527
num_examples: 17366
download_size: 16557512
dataset_size: 72143527
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---