github
/
ChatGLM-6B
mirror of https://github.com/THUDM/ChatGLM-6B
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'main' of github.com:THUDM/ChatGLM-6B

pull/558/merge
duzx16 2023-04-12 09:49:20 +08:00
parent 79e4d8ba8a 0c2806fea8
commit 57e9da3822
2 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ptuning/README.md
View File

@ -126,8 +126,8 @@ gradient_accumulation_steps=1
``` ```
learning_rate=5e-4 learning_rate=5e-4
per_device_train_batch_size=1 per_device_train_batch_size=16
gradient_accumulation_steps=16 gradient_accumulation_steps=1
``` ```

1
ptuning/ds_train_finetune.sh
View File

@ -2,7 +2,6 @@
LR=1e-4 LR=1e-4
MASTER_PORT=$(shuf -n 1 -i 10000-65535) MASTER_PORT=$(shuf -n 1 -i 10000-65535)
MASTER_PORT=50003
deepspeed --num_gpus=4 --master_port $MASTER_PORT main.py \ deepspeed --num_gpus=4 --master_port $MASTER_PORT main.py \
--deepspeed deepspeed.json \ --deepspeed deepspeed.json \