LLaMA-Factory/examples/train_lora/llama3_lora_eval.yaml
codingma 76046dfda8 1. change the task name format
2. delete split param in data_args.py


Former-commit-id: 645211dc01b5d4db3ccd0e3dce03a53860eded26
2024-07-15 09:55:33 +08:00

19 lines
285 B
YAML

### model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
adapter_name_or_path: saves/llama3-8b/lora/sft
### method
finetuning_type: lora
### dataset
task: mmlu_test
template: fewshot
lang: en
n_shot: 5
### output
save_dir: saves/llama3-8b/lora/eval
### eval
batch_size: 4