| ### model | |
| model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct | |
| adapter_name_or_path: saves/llama3-8b/lora/sft | |
| ### method | |
| stage: sft | |
| do_predict: true | |
| finetuning_type: lora | |
| ### dataset | |
| eval_dataset: identity,alpaca_en_demo | |
| template: llama3 | |
| cutoff_len: 1024 | |
| max_samples: 50 | |
| overwrite_cache: true | |
| preprocessing_num_workers: 16 | |
| ### output | |
| output_dir: saves/llama3-8b/lora/predict | |
| overwrite_output_dir: true | |
| ### eval | |
| per_device_eval_batch_size: 1 | |
| predict_with_generate: true | |
| ddp_timeout: 180000000 | |