Name: ENSEONG/stratified-1k-math-private-n256-Qwen2.5-3B-Instruct-bon
Creator: ENSEONG
Published: 2026-03-23 18:04:33
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/ENSEONG/stratified-1k-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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 441775100 num_examples: 1000 download_size: 71965406 dataset_size: 441775100 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 442573395 num_examples: 1000 download_size: 72109233 dataset_size: 442573395 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 441974717 num_examples: 1000 download_size: 71852188 dataset_size: 441974717 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 442822240 num_examples: 1000 download_size: 72030901 dataset_size: 442822240 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 442478016 num_examples: 1000 download_size: 72110546 dataset_size: 442478016 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 441993184 num_examples: 1000 download_size: 71919174 dataset_size: 441993184 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 436329337 num_examples: 1000 download_size: 86987957 dataset_size: 436329337 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 436524949 num_examples: 1000 download_size: 87016847 dataset_size: 436524949 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 436161069 num_examples: 1000 download_size: 86934973 dataset_size: 436161069 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 435799584 num_examples: 1000 download_size: 86992413 dataset_size: 435799584 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 435556612 num_examples: 1000 download_size: 86798243 dataset_size: 435556612 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 435975516 num_examples: 1000 download_size: 86847843 dataset_size: 435975516 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 429760007 num_examples: 1000 download_size: 95247607 dataset_size: 429760007 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 429974986 num_examples: 1000 download_size: 95269244 dataset_size: 429974986 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 429905944 num_examples: 1000 download_size: 95212677 dataset_size: 429905944 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 429419634 num_examples: 1000 download_size: 95171510 dataset_size: 429419634 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 430586976 num_examples: 1000 download_size: 95296555 dataset_size: 430586976 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 429814470 num_examples: 1000 download_size: 95540151 dataset_size: 429814470 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 423717908 num_examples: 1000 download_size: 101060635 dataset_size: 423717908 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 423415863 num_examples: 1000 download_size: 101124224 dataset_size: 423415863 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 424020131 num_examples: 1000 download_size: 101253699 dataset_size: 424020131 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 424227104 num_examples: 1000 download_size: 101269853 dataset_size: 424227104 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 423970936 num_examples: 1000 download_size: 101217641 dataset_size: 423970936 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 423184013 num_examples: 1000 download_size: 101164183 dataset_size: 423184013 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 417943339 num_examples: 1000 download_size: 106132943 dataset_size: 417943339 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 417561493 num_examples: 1000 download_size: 106187016 dataset_size: 417561493 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 417985446 num_examples: 1000 download_size: 106206299 dataset_size: 417985446 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 416799917 num_examples: 1000 download_size: 105898306 dataset_size: 416799917 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 417907433 num_examples: 1000 download_size: 106144618 dataset_size: 417907433 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 417240600 num_examples: 1000 download_size: 106018991 dataset_size: 417240600 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 412099395 num_examples: 1000 download_size: 110492336 dataset_size: 412099395 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 411401432 num_examples: 1000 download_size: 110009092 dataset_size: 411401432 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 411282163 num_examples: 1000 download_size: 110072797 dataset_size: 411282163 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 411495498 num_examples: 1000 download_size: 110560178 dataset_size: 411495498 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 411232728 num_examples: 1000 download_size: 110086431 dataset_size: 411232728 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 411708896 num_examples: 1000 download_size: 110154301 dataset_size: 411708896 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 406821183 num_examples: 1000 download_size: 114841230 dataset_size: 406821183 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 405807978 num_examples: 1000 download_size: 114504986 dataset_size: 405807978 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 406542601 num_examples: 1000 download_size: 114467937 dataset_size: 406542601 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 406504741 num_examples: 1000 download_size: 114424757 dataset_size: 406504741 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 406327194 num_examples: 1000 download_size: 114213920 dataset_size: 406327194 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 405919551 num_examples: 1000 download_size: 114562390 dataset_size: 405919551 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 401856396 num_examples: 1000 download_size: 118524989 dataset_size: 401856396 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 402192138 num_examples: 1000 download_size: 118916715 dataset_size: 402192138 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 402171353 num_examples: 1000 download_size: 119342494 dataset_size: 402171353 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 401874776 num_examples: 1000 download_size: 119027899 dataset_size: 401874776 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 401766561 num_examples: 1000 download_size: 118793498 dataset_size: 401766561 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 401664059 num_examples: 1000 download_size: 119655348 dataset_size: 401664059 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 398802979 num_examples: 1000 download_size: 124702049 dataset_size: 398802979 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 399018244 num_examples: 1000 download_size: 125009633 dataset_size: 399018244 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 399172243 num_examples: 1000 download_size: 124227870 dataset_size: 399172243 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 398931347 num_examples: 1000 download_size: 125074266 dataset_size: 398931347 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 398600629 num_examples: 1000 download_size: 124483748 dataset_size: 398600629 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 399104413 num_examples: 1000 download_size: 124446229 dataset_size: 399104413 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 396578405 num_examples: 1000 download_size: 132040374 dataset_size: 396578405 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 396799059 num_examples: 1000 download_size: 132062503 dataset_size: 396799059 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 396730413 num_examples: 1000 download_size: 132286346 dataset_size: 396730413 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 396536542 num_examples: 1000 download_size: 132170815 dataset_size: 396536542 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 396598099 num_examples: 1000 download_size: 131740668 dataset_size: 396598099 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 396417981 num_examples: 1000 download_size: 132157138 dataset_size: 396417981 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 397608105 num_examples: 1000 download_size: 145886861 dataset_size: 397608105 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 397139422 num_examples: 1000 download_size: 146184268 dataset_size: 397139422 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 397649163 num_examples: 1000 download_size: 146790309 dataset_size: 397649163 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 397485471 num_examples: 1000 download_size: 146171554 dataset_size: 397485471 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 397582299 num_examples: 1000 download_size: 146417032 dataset_size: 397582299 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 397601172 num_examples: 1000 download_size: 146092040 dataset_size: 397601172 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 618569175 num_examples: 1000 download_size: 373822299 dataset_size: 618569175 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 616580997 num_examples: 1000 download_size: 371948452 dataset_size: 616580997 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 616570422 num_examples: 1000 download_size: 371819018 dataset_size: 616570422 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 618586859 num_examples: 1000 download_size: 374261890 dataset_size: 618586859 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 618031468 num_examples: 1000 download_size: 373172294 dataset_size: 618031468 - 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 - name: model_difficulty dtype: int64 splits: - name: train num_bytes: 619987458 num_examples: 1000 download_size: 374914374 dataset_size: 619987458 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：