### model
model_name_or_path: C:\Users\foxba\.cache\modelscope\hub\models\Qwen\Qwen2___5-1___5B-Instruct-GPTQ-Int4

### method
stage: sft
do_train: true
finetuning_type: lora
lora_target: all
quantization_bit: 4
quantization_method: bitsandbytes  # choices: [bitsandbytes (4/8), hqq (2/3/4/5/6/8), eetq (8)]
lora_rank: 16
lora_alpha: 16
lora_dropout: 0.05

### dataset
dataset_dir: ..\dataset
dataset: qwen_dataset
template: qwen
cutoff_len: 1024
overwrite_cache: true
preprocessing_num_workers: 16

### output
output_dir: qlora
logging_steps: 100
save_steps: 100
plot_loss: true
overwrite_output_dir: true

### train
per_device_train_batch_size: 1
gradient_accumulation_steps: 16
learning_rate: 1.0e-4
num_train_epochs: 1.0
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true
ddp_timeout: 180000000

### eval
val_size: 0.1
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 500