llama3_preprocess.yaml

### model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
trust_remote_code: true

### method
stage: sft
do_train: true
finetuning_type: lora
lora_rank: 8
lora_target: all

### dataset
dataset: identity,alpaca_en_demo
template: llama3
cutoff_len: 2048
max_samples: 1000
overwrite_cache: true
preprocessing_num_workers: 16
tokenized_path: saves/llama3-8b/dataset/sft

### output
output_dir: saves/llama3-8b/lora/sft
overwrite_output_dir: true