You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
ColossalAI/applications/Chat/examples/train_sft.sh

29 lines
860 B

set_n_least_used_CUDA_VISIBLE_DEVICES() {
local n=${1:-"9999"}
echo "GPU Memory Usage:"
local FIRST_N_GPU_IDS=$(nvidia-smi --query-gpu=memory.used --format=csv |
tail -n +2 |
nl -v 0 |
tee /dev/tty |
sort -g -k 2 |
awk '{print $1}' |
head -n $n)
export CUDA_VISIBLE_DEVICES=$(echo $FIRST_N_GPU_IDS | sed 's/ /,/g')
echo "Now CUDA_VISIBLE_DEVICES is set to:"
echo "CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES"
}
set_n_least_used_CUDA_VISIBLE_DEVICES 4
torchrun --standalone --nproc_per_node=4 train_sft.py \
--pretrain "/path/to/LLaMa-7B/" \
--model 'llama' \
--strategy colossalai_zero2 \
--save_path /path/to/Coati-7B \
--dataset /path/to/data.json \
--batch_size 4 \
--accumulation_steps 8 \
--lr 2e-5 \
--max_datasets_size 512 \
--max_epochs 1