alpaca-13b-lora / README.md
yahma's picture
Update README.md
e09bb18
|
raw
history blame
803 Bytes
metadata
license: mit
datasets:
  - yahma/alpaca-cleaned

This repo contains a low-rank adapter for LLaMA-13b fit on the Cleaned Alpaca dataset.

This version of the weights was trained with the following hyperparameters:

Cleaned dataset: Snapshot April 9, 2023
Epochs: 4
Validation set size: 1500
Batch size: 128
Micro batch size: 4
Cutoff length: 512
Learning rate: 3e-4
Lora r: 16
Lora target modules: q_proj, k_proj, v_proj, o_proj

That is:

python finetune.py
--base_model='decapoda-research/llama-13b-hf'
--data_path 'yahma/alpaca-cleaned'
--num_epochs=4
--cutoff_len=512
--output_dir='./lora-alpaca'
--lora_target_modules='[q_proj,k_proj, v_proj, o_proj]'
--lora_r=16
--val_set_size 1500
--micro_batch_size=4