composer_replication/recipes/replaysim/default.yaml

# Default replaysim normalization recipe.
#
# This is a data-juicer YAML config (https://github.com/modelscope/data-juicer).
# It runs CPU-only ops that filter and clean DPO pairs produced by
# composer_replication.teacher_replay.extract_dpo_pairs.
#
# The op-graph operates on records of shape:
#
#     {
#       "state_id": "...",
#       "messages":  [{"role": "user",      "content": "..."}],   # context
#       # --- flat-string shape (consumed by length/word/special-char/dedup filters) ---
#       "chosen":    "the chosen response as a plain string",
#       "rejected":  "the rejected response as a plain string",
#       # --- chat-messages shape (preserved for chat-aware ops + round-trip) ---
#       "chosen_messages":   [{"role": "assistant", "content": "..."}],
#       "rejected_messages": [{"role": "assistant", "content": "..."}],
#       "n_teachers_agreeing": 2
#     }
#
# IMPORTANT — field-key contract:
# data-juicer's `text_length_filter`, `words_num_filter`,
# `special_characters_filter` and `document_deduplicator` all read a SINGLE
# string field named by `text_key` (singular). They expect plain strings.
# Pointing them at a list-of-dicts (the chat-messages shape) crashes or
# silently no-ops. We therefore keep two parallel representations:
#   * `chosen` / `rejected`             — plain strings, fed to filter ops below.
#   * `chosen_messages` / `rejected_messages` — chat-messages list, preserved
#     untouched for downstream chat-aware consumers and the round-trip.
#
# data-juicer caveat: each filter op accepts only ONE `text_key`. To filter
# both `chosen` AND `rejected`, we duplicate each op — once with
# `text_key: chosen`, once with `text_key: rejected`. The top-level
# `text_keys: chosen` below also satisfies data-juicer's dataset-load
# validation (the formatter checks the global text_key exists in the dataset).
#
# Ops listed in `process` are applied in order. Each op operates on the
# full record but reads/writes one field.

# Project & I/O are filled in by DJNormalizer at runtime; we only
# specify the op pipeline here.

# --- Global text-key contract (see header note) -----------------------
# data-juicer validates this exists on the dataset before any op runs, and
# uses it as the default text_key for ops that don't specify their own.
text_keys: chosen

# --- Op pipeline (applied in order) -----------------------------------
process:

  # 1. Length filter on the assistant response.
  #    Drops pairs where either the chosen or rejected response is shorter
  #    than 8 chars or longer than 32k chars (likely garbled / overflow).
  - text_length_filter:
      min_len: 8
      max_len: 32000
      text_key: chosen
  - text_length_filter:
      min_len: 8
      max_len: 32000
      text_key: rejected

  # 2. Word-count filter on response.
  #    Drops pairs with absurdly low (< 2 words) or high (> 4096 words)
  #    response counts.
  - words_num_filter:
      min_num: 2
      max_num: 4096
      text_key: chosen
  - words_num_filter:
      min_num: 2
      max_num: 4096
      text_key: rejected

  # 3. Special-character filter.
  #    Drops responses where >50% of characters are non-alphabetic
  #    special chars (likely encoding errors or junk).
  - special_characters_filter:
      max_ratio: 0.5
      text_key: chosen
  - special_characters_filter:
      max_ratio: 0.5
      text_key: rejected

  # 4. Per-conversation deduplication.
  #    Within the batch, drop records where the `chosen` field is a
  #    duplicate of another record's `chosen`. (data-juicer's
  #    document_deduplicator is per-batch hashing — full-corpus dedup is
  #    a separate op family.)
  - document_deduplicator:
      lowercase: true
      ignore_non_character: true
      text_key: chosen

# Notes:
# - We DO NOT run `pair_preference_mapper` because its default config may
#   re-synthesize the rejected text via an LLM call — we already have
#   real disagreement-derived rejected text and don't want to pay another
#   API call. (See ADR-004 § "One-day spike before merge.")
# - Language detection is intentionally not in the default — it requires
#   downloading a fasttext model and adds startup latency. Add the
#   `language_id_score_filter` op to a custom recipe if needed.
# - Semantic-similarity dedup is GPU-bound (NeMo-Curator ops); not in
#   the default.