# Synthetic-data workflow recipe (v0.53.9 #12)
#
# Pairs with `examples/synthetic_workflow.md`. Trains TinyLlama-1.1B on
# a JSONL produced by:
#   soup data generate --provider ollama --output ./synth_raw.jsonl
#   soup data filter --input ./synth_raw.jsonl --output ./synth_filtered.jsonl
#   soup data score --input ./synth_filtered.jsonl --output ./synth_scored.jsonl
#   soup data decontaminate --input ./synth_scored.jsonl \
#       --output ./synth_clean.jsonl --benchmarks mmlu,gsm8k

base: TinyLlama/TinyLlama-1.1B-Chat-v1.0
task: sft
modality: text
backend: transformers

data:
  train: ./synth_clean.jsonl
  format: auto
  val_split: 0.05
  max_length: 1024

training:
  epochs: 1
  lr: 2.0e-4
  batch_size: auto
  quantization: 4bit
  optimizer: adamw_torch
  scheduler: cosine
  gradient_checkpointing: true
  warmup_auto: true
  auto_mixed_precision: true
  lora:
    r: 8
    alpha: 16
    dropout: 0.05

output: ./synth_out

eval:
  auto_eval: false