redpajama-cc-2022-05-refine.yaml

# global parameters
project_name: 'Data-Juicer-recipes-cc-2022-05'
dataset_path: '/path/to/your/dataset'  # path to your dataset directory or file
export_path: '/path/to/your/dataset.jsonl'

np: 50  # number of subprocess to process your dataset
open_tracer: true

# process schedule
# a list of several process operators with their arguments
process:
  - document_simhash_deduplicator:
      tokenization: space
      window_size: 6
      lowercase: true
      ignore_pattern: '\p{P}'
      num_blocks: 6
      hamming_distance: 4

  - clean_email_mapper:
  - clean_links_mapper:
  - fix_unicode_mapper:
  - punctuation_normalization_mapper:
  - whitespace_normalization_mapper:

  - alphanumeric_filter:
      tokenization: false
      min_ratio: 0.7514  # 3sigma
      max_ratio: 0.8577  # 3sigmai -- 888003
  - average_line_length_filter:  # for code
      max_len: 1500  # < 3sigma -- 447069
  - character_repetition_filter:
      rep_len: 10
      max_ratio: 0.3  # > 3sigma -- 145890 samples
  - flagged_words_filter:
      lang: en
      tokenization: true
      max_ratio: 0.0012  # 3sigma -- 319395
  - language_id_score_filter:  # remove language filter
      min_score: 0.791  # 3sigma -- 1823528
  - maximum_line_length_filter:  # for code
      max_len: 5000  # < 3sigma -- 791612
  - perplexity_filter:
      lang: en
      max_ppl: 5000  # < 3sigma -- 654459
  - special_characters_filter:
      min_ratio: 0.15  # > 3sigma
      max_ratio: 0.35  # > 3sigma
  - text_length_filter:
      max_len: 59265  # 3sigma -- 1046590
  - words_num_filter:
      lang: en
      tokenization: true
      min_num: 20  # > 3sigma
      max_num: 11860  # 3sigma -- 1036780
  - word_repetition_filter:
      lang: en
      tokenization: true
      rep_len: 10
      max_ratio: 0.3117  # 3sigma -- 2089703