mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-10-16 00:28:10 +08:00
40 lines
731 B
YAML
40 lines
731 B
YAML
### model
|
|
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
|
|
|
|
### method
|
|
stage: sft
|
|
do_train: true
|
|
finetuning_type: full
|
|
mixture_of_depths: convert
|
|
|
|
### dataset
|
|
dataset: identity,alpaca_en_demo
|
|
template: llama3
|
|
cutoff_len: 1024
|
|
max_samples: 1000
|
|
overwrite_cache: true
|
|
preprocessing_num_workers: 16
|
|
|
|
### output
|
|
output_dir: saves/llama3-8b-mod/full/sft
|
|
logging_steps: 10
|
|
save_steps: 500
|
|
plot_loss: true
|
|
overwrite_output_dir: true
|
|
|
|
### train
|
|
per_device_train_batch_size: 1
|
|
gradient_accumulation_steps: 8
|
|
optim: paged_adamw_8bit
|
|
learning_rate: 0.0001
|
|
num_train_epochs: 3.0
|
|
lr_scheduler_type: cosine
|
|
warmup_steps: 0.1
|
|
pure_bf16: true
|
|
|
|
### eval
|
|
val_size: 0.1
|
|
per_device_eval_batch_size: 1
|
|
evaluation_strategy: steps
|
|
eval_steps: 500
|