Witllm/qwen/finetune_qlora_ds.sh

94 lines
2.6 KiB
Bash
Executable File

#!/bin/bash
export CUDA_DEVICE_MAX_CONNECTIONS=1
DIR=`pwd`
# Guide:
# This script supports distributed training on multi-gpu workers (as well as single-worker training).
# Please set the options below according to the comments.
# For multi-gpu workers training, these options should be manually set for each worker.
# After setting the options, please run the script on each worker.
# Number of GPUs per GPU worker
GPUS_PER_NODE=$(python -c 'import torch; print(torch.cuda.device_count())')
# Number of GPU workers, for single-worker training, please set to 1
NNODES=${NNODES:-1}
# The rank of this worker, should be in {0, ..., WORKER_CNT-1}, for single-worker training, please set to 0
NODE_RANK=${NODE_RANK:-0}
# The ip address of the rank-0 worker, for single-worker training, please set to localhost
MASTER_ADDR=${MASTER_ADDR:localhost}
# The port for communication
MASTER_PORT=${MASTER_PORT:-6001}
MODEL="Qwen/Qwen-7B-Chat-Int4" # Set the path if you do not want to load from huggingface directly
# ATTENTION: specify the path to your training data, which should be a json file consisting of a list of conversations.
# See the section for finetuning in README for more information.
DATA="path_to_data"
function usage() {
echo '
Usage: bash finetune/finetune_qlora_ds.sh [-m MODEL_PATH] [-d DATA_PATH]
'
}
while [[ "$1" != "" ]]; do
case $1 in
-m | --model )
shift
MODEL=$1
;;
-d | --data )
shift
DATA=$1
;;
-h | --help )
usage
exit 0
;;
* )
echo "Unknown argument ${1}"
exit 1
;;
esac
shift
done
DISTRIBUTED_ARGS="
--nproc_per_node $GPUS_PER_NODE \
--nnodes $NNODES \
--node_rank $NODE_RANK \
--master_addr $MASTER_ADDR \
--master_port $MASTER_PORT
"
# Remember to use --fp16 instead of --bf16 due to autogptq
torchrun $DISTRIBUTED_ARGS finetune.py \
--model_name_or_path $MODEL \
--data_path $DATA \
--fp16 True \
--output_dir output_qwen \
--num_train_epochs 5 \
--per_device_train_batch_size 2 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 8 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 1000 \
--save_total_limit 10 \
--learning_rate 3e-4 \
--weight_decay 0.1 \
--adam_beta2 0.95 \
--warmup_ratio 0.01 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--report_to "none" \
--model_max_length 512 \
--lazy_preprocess True \
--use_lora \
--q_lora \
--gradient_checkpointing \
--deepspeed finetune/ds_config_zero2.json