Name: ENSEONG/preprocessed-full-math-private-n256-Qwen2.5-3B-Instruct-bon
Creator: ENSEONG
Published: 2026-03-23 16:40:08
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/ENSEONG/preprocessed-full-math-private-n256-Qwen2.5-3B-Instruct-bon

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1906828109 num_examples: 5000 download_size: 283734563 dataset_size: 1906828109 - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1909834194 num_examples: 5000 download_size: 283952813 dataset_size: 1909834194 - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1908443070 num_examples: 5000 download_size: 283749242 dataset_size: 1908443070 - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1908237893 num_examples: 5000 download_size: 283295773 dataset_size: 1908237893 - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1908243731 num_examples: 5000 download_size: 283342247 dataset_size: 1908243731 - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1908265252 num_examples: 5000 download_size: 283258603 dataset_size: 1908265252 - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1892774231 num_examples: 5000 download_size: 348023906 dataset_size: 1892774231 - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1892718360 num_examples: 5000 download_size: 348276483 dataset_size: 1892718360 - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1892256572 num_examples: 5000 download_size: 347825749 dataset_size: 1892256572 - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1892988076 num_examples: 5000 download_size: 347886613 dataset_size: 1892988076 - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1891359049 num_examples: 5000 download_size: 347729376 dataset_size: 1891359049 - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1895011858 num_examples: 5000 download_size: 348777710 dataset_size: 1895011858 - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1873581541 num_examples: 5000 download_size: 387426934 dataset_size: 1873581541 - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1874208113 num_examples: 5000 download_size: 387500130 dataset_size: 1874208113 - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1873108933 num_examples: 5000 download_size: 387203630 dataset_size: 1873108933 - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1873530536 num_examples: 5000 download_size: 387027096 dataset_size: 1873530536 - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1873735030 num_examples: 5000 download_size: 387250881 dataset_size: 1873735030 - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1872382226 num_examples: 5000 download_size: 387488147 dataset_size: 1872382226 - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1851727223 num_examples: 5000 download_size: 415689524 dataset_size: 1851727223 - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1852249369 num_examples: 5000 download_size: 416083579 dataset_size: 1852249369 - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1852048959 num_examples: 5000 download_size: 415680982 dataset_size: 1852048959 - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1852455981 num_examples: 5000 download_size: 415849904 dataset_size: 1852455981 - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1852458580 num_examples: 5000 download_size: 415820411 dataset_size: 1852458580 - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1851228055 num_examples: 5000 download_size: 416048276 dataset_size: 1851228055 - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1829222506 num_examples: 5000 download_size: 439324970 dataset_size: 1829222506 - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1829203868 num_examples: 5000 download_size: 439466223 dataset_size: 1829203868 - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1830465530 num_examples: 5000 download_size: 439732217 dataset_size: 1830465530 - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1828135202 num_examples: 5000 download_size: 439297594 dataset_size: 1828135202 - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1829530646 num_examples: 5000 download_size: 439423075 dataset_size: 1829530646 - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1829420569 num_examples: 5000 download_size: 439239199 dataset_size: 1829420569 - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1808252298 num_examples: 5000 download_size: 460516711 dataset_size: 1808252298 - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1808011927 num_examples: 5000 download_size: 460247731 dataset_size: 1808011927 - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1806621778 num_examples: 5000 download_size: 460373372 dataset_size: 1806621778 - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1807424345 num_examples: 5000 download_size: 460355440 dataset_size: 1807424345 - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1806592153 num_examples: 5000 download_size: 460561632 dataset_size: 1806592153 - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1808004657 num_examples: 5000 download_size: 460025621 dataset_size: 1808004657 - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1788654046 num_examples: 5000 download_size: 481118734 dataset_size: 1788654046 - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1787024580 num_examples: 5000 download_size: 480441003 dataset_size: 1787024580 - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1789195474 num_examples: 5000 download_size: 481442966 dataset_size: 1789195474 - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1787879701 num_examples: 5000 download_size: 480757700 dataset_size: 1787879701 - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1787697652 num_examples: 5000 download_size: 480694191 dataset_size: 1787697652 - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1787169027 num_examples: 5000 download_size: 480763945 dataset_size: 1787169027 - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1770469148 num_examples: 5000 download_size: 501032284 dataset_size: 1770469148 - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1771319814 num_examples: 5000 download_size: 501168890 dataset_size: 1771319814 - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1771897510 num_examples: 5000 download_size: 501529747 dataset_size: 1771897510 - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1770858622 num_examples: 5000 download_size: 501279484 dataset_size: 1770858622 - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1770729570 num_examples: 5000 download_size: 501323887 dataset_size: 1770729570 - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1771374437 num_examples: 5000 download_size: 501961872 dataset_size: 1771374437 - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1758844458 num_examples: 5000 download_size: 526022146 dataset_size: 1758844458 - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1758127430 num_examples: 5000 download_size: 525815610 dataset_size: 1758127430 - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1759003923 num_examples: 5000 download_size: 525444684 dataset_size: 1759003923 - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1758222070 num_examples: 5000 download_size: 526232711 dataset_size: 1758222070 - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1758469144 num_examples: 5000 download_size: 526092343 dataset_size: 1758469144 - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1758274327 num_examples: 5000 download_size: 526081671 dataset_size: 1758274327 - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1748720353 num_examples: 5000 download_size: 558073772 dataset_size: 1748720353 - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1748240802 num_examples: 5000 download_size: 557572591 dataset_size: 1748240802 - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1747319939 num_examples: 5000 download_size: 557746094 dataset_size: 1747319939 - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1748387598 num_examples: 5000 download_size: 558712570 dataset_size: 1748387598 - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1748625158 num_examples: 5000 download_size: 558509145 dataset_size: 1748625158 - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1747401953 num_examples: 5000 download_size: 558438315 dataset_size: 1747401953 - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1752882468 num_examples: 5000 download_size: 618257078 dataset_size: 1752882468 - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1752026064 num_examples: 5000 download_size: 616951355 dataset_size: 1752026064 - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1753208362 num_examples: 5000 download_size: 617266951 dataset_size: 1753208362 - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1752805891 num_examples: 5000 download_size: 618086001 dataset_size: 1752805891 - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1752652530 num_examples: 5000 download_size: 617400820 dataset_size: 1752652530 - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 1751944156 num_examples: 5000 download_size: 616316513 dataset_size: 1751944156 - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-0--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 2619227943 num_examples: 5000 download_size: 1509416869 dataset_size: 2619227943 - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-128--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 2611824650 num_examples: 5000 download_size: 1502484460 dataset_size: 2611824650 - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-256--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 2618304015 num_examples: 5000 download_size: 1508849471 dataset_size: 2618304015 - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-42--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 2618169008 num_examples: 5000 download_size: 1509235187 dataset_size: 2618169008 - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-512--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 2617780359 num_examples: 5000 download_size: 1507541551 dataset_size: 2617780359 - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-64--agg_strategy-last features: - name: problem dtype: string - name: level dtype: string - name: type dtype: string - name: solution dtype: string - name: answer dtype: string - name: completions list: string - name: scores list: 'null' - name: pred dtype: string - name: completion_tokens list: int64 - name: pred_maj@1 dtype: string - name: pred_maj@2 dtype: string - name: pred_maj@4 dtype: string - name: pred_maj@8 dtype: string - name: pred_maj@16 dtype: string - name: pred_maj@32 dtype: string - name: pred_maj@64 dtype: string - name: pred_maj@128 dtype: string - name: pred_maj@256 dtype: string - name: preds list: string - name: pass@1 dtype: float64 - name: pass@2 dtype: float64 - name: pass@4 dtype: float64 - name: pass@8 dtype: float64 - name: pass@16 dtype: float64 - name: pass@32 dtype: float64 - name: pass@64 dtype: float64 - name: pass@128 dtype: float64 - name: pass@256 dtype: float64 - name: is_correct_maj@1 dtype: bool - name: is_correct_maj@2 dtype: bool - name: is_correct_maj@4 dtype: bool - name: is_correct_maj@8 dtype: bool - name: is_correct_maj@16 dtype: bool - name: is_correct_maj@32 dtype: bool - name: is_correct_maj@64 dtype: bool - name: is_correct_maj@128 dtype: bool - name: is_correct_maj@256 dtype: bool - name: is_correct_preds list: bool - name: _preprocessing_metadata struct: - name: num_pred_fields dtype: int64 - name: preprocessed_at dtype: string - name: preprocessing_version dtype: string - name: total_evaluations dtype: int64 splits: - name: train num_bytes: 2623119556 num_examples: 5000 download_size: 1513252102 dataset_size: 2623119556 configs: - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.1--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.2--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.3--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.4--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.5--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.6--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.7--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.8--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-0.9--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.0--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.1--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-0--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-0--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-128--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-128--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-256--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-256--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-42--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-42--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-512--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-512--agg_strategy-last/train-* - config_name: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-64--agg_strategy-last data_files: - split: train path: ENSEONG_math-private--T-1.2--top_p-1.0--n-256--seed-64--agg_strategy-last/train-* ---

应用场景：