p04798526
/
CPM-9G-8B
forked from jiuyuan/CPM-9G-8B
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compare commits

base: p04798526:929a5bd6675c6167c3410d488a750b3ad38a8c8e
Branches Tags
p04798526:FM_9G
p04798526:master
jiuyuan:master
jiuyuan:FM_9G
..
compare: p04798526:41a67e697b96b37ac3798c1f84d495b5834984e3
Branches Tags
p04798526:master
p04798526:FM_9G
jiuyuan:master
jiuyuan:FM_9G

2 Commits
929a5bd667 ... 41a67e697b

Author SHA1 Message Date
wql 41a67e697b fix: change port 2024-08-26 16:15:28 +08:00
wql 0fa3b02384 fix: fix nproc 2024-08-26 16:14:58 +08:00
1 changed files with 2 additions and 2 deletions
Show Stats Expand all files Collapse all files

4
9g_lora_0.sh
View File

@ -1,7 +1,7 @@
#! /bin/bash
export MASTER_ADDR="localhost"
export MASTER_PORT=12390
export MASTER_PORT=12400
CPM_PATH="/workspace/repo/CPM-9G-8B/9G-Train"
@ -50,7 +50,7 @@ OPTS+=" --lora-layer project_q project_v project_k w_0 w_1 w_out"
OPTS+=" $@"
CMD="torchrun --nnodes=1 --nproc_per_node=7 --rdzv_id=1 --rdzv_backend=c10d --rdzv_endpoint=${MASTER_ADDR}:${MASTER_PORT} ${CPM_PATH}/apps/cpm9g/sft_cpm9g_delta.py ${OPTS}"
CMD="torchrun --nnodes=1 --nproc_per_node=6 --rdzv_id=1 --rdzv_backend=c10d --rdzv_endpoint=${MASTER_ADDR}:${MASTER_PORT} ${CPM_PATH}/apps/cpm9g/sft_cpm9g_delta.py ${OPTS}"
echo "${CMD}"
$CMD