| ### model | |
| model_name_or_path: Qwen/Qwen3-0.6B | |
| quantization_bit: 4 # choices: [8 (bnb/hqq/eetq), 4 (bnb/hqq), 3 (hqq), 2 (hqq)] | |
| quantization_method: bnb # choices: [bnb, hqq, eetq] | |
| trust_remote_code: true | |
| ### method | |
| stage: sft | |
| do_train: true | |
| finetuning_type: lora | |
| lora_rank: 8 | |
| lora_target: all | |
| ### dataset | |
| dataset: alpaca_en_demo | |
| template: qwen3 | |
| cutoff_len: 2048 | |
| max_samples: 1000 | |
| overwrite_cache: true | |
| preprocessing_num_workers: 16 | |
| dataloader_num_workers: 4 | |
| ### output | |
| output_dir: saves/qwen3-0.6b/lora/sft | |
| logging_steps: 10 | |
| save_steps: 500 | |
| plot_loss: true | |
| overwrite_output_dir: true | |
| save_only_model: false | |
| report_to: none # choices: [none, wandb, tensorboard, swanlab, mlflow] | |
| ### train | |
| per_device_train_batch_size: 1 | |
| gradient_accumulation_steps: 8 | |
| learning_rate: 1.0e-4 | |
| num_train_epochs: 3.0 | |
| 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 | |