2024-05-06 22:51:02 +08:00
|
|
|
# model
|
|
|
|
|
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
|
|
|
|
|
|
|
|
|
|
# method
|
|
|
|
|
stage: sft
|
|
|
|
|
do_train: true
|
|
|
|
|
finetuning_type: full
|
|
|
|
|
use_galore: true
|
|
|
|
|
galore_layerwise: true
|
|
|
|
|
galore_target: mlp,self_attn
|
|
|
|
|
galore_rank: 128
|
|
|
|
|
galore_scale: 2.0
|
|
|
|
|
|
|
|
|
|
# dataset
|
|
|
|
|
dataset: identity,alpaca_gpt4_en
|
|
|
|
|
template: llama3
|
|
|
|
|
cutoff_len: 1024
|
|
|
|
|
max_samples: 1000
|
|
|
|
|
overwrite_cache: true
|
|
|
|
|
preprocessing_num_workers: 16
|
|
|
|
|
|
|
|
|
|
# output
|
|
|
|
|
output_dir: saves/llama3-8b/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: 1
|
|
|
|
|
learning_rate: 0.0001
|
|
|
|
|
num_train_epochs: 3.0
|
|
|
|
|
lr_scheduler_type: cosine
|
|
|
|
|
warmup_steps: 0.1
|
|
|
|
|
pure_bf16: true
|
|
|
|
|
|
|
|
|
|
# eval
|
2024-05-13 20:39:36 +08:00
|
|
|
val_size: 0.1
|
2024-05-06 22:51:02 +08:00
|
|
|
per_device_eval_batch_size: 1
|
|
|
|
|
evaluation_strategy: steps
|
|
|
|
|
eval_steps: 500
|
