mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-05-28 18:05:56 +00:00
df5e9c53cf
* Add dpo. Fix sft, ppo, lora. Refactor all * fix and tested ppo * 2 nd round refactor * add ci tests * fix ci * fix ci * fix readme, style * fix readme style * fix style, fix benchmark * reproduce benchmark result, remove useless files * rename to ColossalChat * use new image * fix ci workflow * fix ci * use local model/tokenizer for ci tests * fix ci * fix ci * fix ci * fix ci timeout * fix rm progress bar. fix ci timeout * fix ci * fix ci typo * remove 3d plugin from ci temporary * test environment * cannot save optimizer * support chat template * fix readme * fix path * test ci locally * restore build_or_pr * fix ci data path * fix benchmark * fix ci, move ci tests to 3080, disable fast tokenizer * move ci to 85 * support flash attention 2 * add all-in-one data preparation script. Fix colossal-llama2-chat chat template * add hardware requirements * move ci test data * fix save_model, add unwrap * fix missing bos * fix missing bos; support grad accumulation with gemini * fix ci * fix ci * fix ci * fix llama2 chat template config * debug sft * debug sft * fix colossalai version requirement * fix ci * add sanity check to prevent NaN loss * fix requirements * add dummy data generation script * add dummy data generation script * add dummy data generation script * add dummy data generation script * update readme * update readme * update readme and ignore * fix logger bug * support parallel_output * modify data preparation logic * fix tokenization * update lr * fix inference * run pre-commit --------- Co-authored-by: Tong Li <tong.li352711588@gmail.com>
60 lines
2.1 KiB
Bash
Executable File
60 lines
2.1 KiB
Bash
Executable File
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"
|
|
}
|
|
|
|
|
|
# export CUDA_VISIBLE_DEVICES=4,5,6
|
|
set_n_least_used_CUDA_VISIBLE_DEVICES 4
|
|
PROJECT_NAME="sft"
|
|
PARENT_SAVE_DIR="" # Path to a folder to save checkpoints
|
|
PARENT_TENSORBOARD_DIR="" # Path to a folder to save logs
|
|
PARENT_CONFIG_FILE="" # Path to a folder to save training config logs
|
|
PRETRAINED_MODEL_PATH="" # huggingface or local model path
|
|
PRETRAINED_TOKENIZER_PATH="" # huggingface or local tokenizer path
|
|
declare -a dataset=(
|
|
YOUR/SFT/DATA/DIR/arrow/part-00000
|
|
YOUR/SFT/DATA/DIR/arrow/part-00001
|
|
YOUR/SFT/DATA/DIR/arrow/part-00002
|
|
YOUR/SFT/DATA/DIR/arrow/part-00003
|
|
YOUR/SFT/DATA/DIR/arrow/part-00004
|
|
YOUR/SFT/DATA/DIR/arrow/part-00005
|
|
YOUR/SFT/DATA/DIR/arrow/part-00006
|
|
YOUR/SFT/DATA/DIR/arrow/part-00007
|
|
YOUR/SFT/DATA/DIR/arrow/part-00008
|
|
YOUR/SFT/DATA/DIR/arrow/part-00009
|
|
)
|
|
|
|
TIMESTAMP=$(date +%Y-%m-%d-%H-%M-%S)
|
|
FULL_PROJECT_NAME="${PROJECT_NAME}-${TIMESTAMP}"
|
|
SAVE_DIR="${PARENT_SAVE_DIR}${FULL_PROJECT_NAME}"
|
|
CONFIG_FILE="${PARENT_CONFIG_FILE}-${FULL_PROJECT_NAME}.json"
|
|
|
|
# the real batch size for gradient descent is number_of_node_in_hostfile * nproc_per_node * train_batch_size
|
|
colossalai run --nproc_per_node 4 --master_port 31312 --hostfile ./hostfile train_sft.py \
|
|
--pretrain $PRETRAINED_MODEL_PATH \
|
|
--tokenizer_dir $PRETRAINED_TOKENIZER_PATH \
|
|
--save_interval 4000 \
|
|
--dataset ${dataset[@]} \
|
|
--save_path $SAVE_DIR \
|
|
--config_file $CONFIG_FILE \
|
|
--lora_rank 0 \
|
|
--plugin zero2 \
|
|
--batch_size 8 \
|
|
--max_epochs 1 \
|
|
--accumulation_steps 1 \
|
|
--lr 2e-5 \
|
|
--max_len 2048 \
|
|
--grad_checkpoint \
|
|
--use_wandb
|