# QLoRA fine-tuning configuration for the kushya generator.
# Architecture §3.6.

base_model:
  name: mistralai/Mistral-Small-Instruct-2409  # Mistral Medium 3.1 weights when available
  trust_remote_code: false
  load_in_4bit: true
  bnb_4bit_compute_dtype: bfloat16
  bnb_4bit_quant_type: nf4
  bnb_4bit_use_double_quant: true

lora:
  r: 32
  alpha: 64
  dropout: 0.05
  bias: none
  task_type: CAUSAL_LM
  target_modules:
    - q_proj
    - k_proj
    - v_proj
    - o_proj
    - gate_proj
    - up_proj
    - down_proj

training:
  output_dir: ./adapter
  num_train_epochs: 3
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 16
  gradient_checkpointing: true
  optim: paged_adamw_8bit
  learning_rate: 2.0e-4
  lr_scheduler_type: cosine
  warmup_ratio: 0.03
  weight_decay: 0.0
  max_grad_norm: 0.3
  fp16: false
  bf16: true
  logging_steps: 10
  evaluation_strategy: steps
  eval_steps: 50
  save_strategy: epoch
  save_total_limit: 2
  group_by_length: true
  report_to: none
  seed: 42

data:
  train_file: ../data/train.jsonl
  eval_file: ../data/eval.jsonl
  max_seq_length: 1024
  prompt_template: |
    [INST] You are a Talmudic challenger. Your single function is to
    generate the strongest possible kushya (challenge) to a proposed
    Torah interpretation. Your kushya MUST:
      1. Reference a specific Torah passage that creates tension
      2. Identify the logical or textual weakness
      3. Be expressed as a question, not a statement
      4. Not be resolvable by trivial clarification

    {input}
    [/INST]
    {output}