[Colossal-LLaMA] Refactor latest APIs (#6030)

* refactor latest code

* update api

* add dummy dataset

* update Readme

* add setup

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update files

* add PP support

* update arguments

* update argument

* reorg folder

* update version

* remove IB infor

* update utils

* update readme

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update save for zero

* update save

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* add apex

* update

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Tong Li
2024-08-28 17:01:58 +08:00
committed by GitHub
parent cc1b0efc17
commit 4a68efb7da
13 changed files with 397 additions and 549 deletions

View File

@@ -1,13 +1,20 @@
#!/bin/bash
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"
}
# NCCL IB environment variables
export NCCL_IB_HCA=mlx5_1:1,mlx5_2:1,mlx5_3:1,mlx5_4:1
export NCCL_IB_DISABLE=0
export NCCL_SOCKET_IFNAME=eth0
export NCCL_IB_GID_INDEX=3
export NCCL_IB_TIMEOUT=23
export NCCL_IB_RETRY_CNT=7
export OMP_NUM_THREADS=8
set_n_least_used_CUDA_VISIBLE_DEVICES 8
PROJECT_NAME=""
PARENT_SAVE_DIR=""