bluecopa/samyx-classifier-train-v3

--- dataset_info: features: - name: doc_id dtype: string - name: dataset dtype: string - name: field dtype: string - name: field_type dtype: string - name: gold dtype: string - name: lilt_span dtype: string - name: gemma_pred dtype: string - name: status dtype: string - name: correct dtype: int64 - name: feat_lilt_confidence dtype: float64 - name: feat_qwen_min_logprob dtype: float64 - name: feat_format_match dtype: float64 - name: feat_pred_length dtype: float64 - name: feat_pred_word_count dtype: float64 - name: feat_alpha_ratio dtype: float64 - name: feat_digit_ratio dtype: float64 - name: feat_exact_substring dtype: float64 - name: feat_word_overlap dtype: float64 - name: feat_doc_token_count dtype: float64 - name: feat_ftype_entity dtype: float64 - name: feat_ftype_date dtype: float64 - name: feat_ftype_amount dtype: float64 - name: feat_ftype_text dtype: float64 - name: feat_span_length dtype: float64 - name: feat_span_change_ratio dtype: float64 - name: feat_span_pred_overlap dtype: float64 - name: feat_lilt_gemma_fuzzy dtype: float64 - name: feat_lilt_gemma_word_overlap dtype: float64 - name: feat_date_parses dtype: float64 - name: feat_amount_parses dtype: float64 - name: feat_n_source_occurrences dtype: float64 - name: feat_n_ser_value_spans dtype: float64 splits: - name: train num_bytes: 20020916 num_examples: 61145 download_size: 3143476 dataset_size: 20020916 configs: - config_name: default data_files: - split: train path: data/train-* ---