LLaMA-Factory-Mirror/examples/extras/llama_pro/llama3_freeze_sft.yaml

42 lines
776 B
YAML

### model
model_name_or_path: models/llama3-8b-instruct-pro
### method
stage: sft
do_train: true
finetuning_type: freeze
freeze_trainable_layers: 8
freeze_trainable_modules: all
use_llama_pro: true
### 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-instruct-pro/freeze/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
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