pattern_targets.yaml

# Pattern-filtered target masking.
#
# Not every assistant turn deserves KL loss — only those whose content
# matches a regex. Useful when your data mixes chain-of-thought with
# final answers and you only want to distill the final answers, or when
# you want to bake only the "structured" portion of multi-style replies.
#
# Here: only assistant messages whose content starts with "Answer:" are
# treated as targets. Everything else (system, user, non-matching
# assistant turns) is passed through to both teacher and student but
# contributes zero loss.
#
# Usage:
#   bakery --config examples/pattern_targets.yaml

# --- Standard TrainingArguments ---
output_dir: "./outputs/pattern_targets"
num_train_epochs: 2
learning_rate: 1e-4
per_device_train_batch_size: 2
gradient_accumulation_steps: 2
logging_steps: 5
save_strategy: "epoch"
bf16: true
report_to: "none"
seed: 42

# --- Context baking ---
prefix_messages:
  - role: system
    content: >-
      Reason step-by-step, then give a final answer on a new line
      beginning with "Answer: ".

student_retained_turns: 0
target_roles:
  - assistant

# Only tokens from assistant messages that match this regex (re.search)
# are scored by KL. CoT / reasoning prefixes are ignored.
target_content_pattern: "^Answer:"

# --- Model ---
model_name_or_path: "Qwen/Qwen3-0.6B"
torch_dtype: "bfloat16"
attn_implementation: "sdpa"

# --- LoRA ---
r: 32
lora_alpha: 64
target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
lora_dropout: 0.05

# --- Data ---
training_prompts:
  - "What is 17 times 3?"
  - "If a train leaves at 3pm traveling 60mph, where is it at 5pm?"
  - "How many vowels are in the word 'strawberry'?"