mirror of https://github.com/THUDM/ChatGLM2-6B
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.
29 lines
768 B
29 lines
768 B
1 year ago
|
|
||
|
|
LR=1e-4
|
||
|
|
|
||
|
|
MASTER_PORT=$(shuf -n 1 -i 10000-65535)
|
||
|
|
|
||
|
|
deepspeed --num_gpus=4 --master_port $MASTER_PORT main.py \
|
||
|
|
--deepspeed deepspeed.json \
|
||
|
|
--do_train \
|
||
|
|
--train_file AdvertiseGen/train.json \
|
||
|
|
--test_file AdvertiseGen/dev.json \
|
||
|
|
--prompt_column content \
|
||
|
|
--response_column summary \
|
||
|
|
--overwrite_cache \
|
||
|
|
--model_name_or_path THUDM/chatglm2-6b \
|
||
|
|
--output_dir ./output/adgen-chatglm2-6b-ft-$LR \
|
||
|
|
--overwrite_output_dir \
|
||
|
|
--max_source_length 64 \
|
||
|
|
--max_target_length 64 \
|
||
|
|
--per_device_train_batch_size 4 \
|
||
|
|
--per_device_eval_batch_size 1 \
|
||
|
|
--gradient_accumulation_steps 1 \
|
||
|
|
--predict_with_generate \
|
||
|
|
--max_steps 5000 \
|
||
|
|
--logging_steps 10 \
|
||
|
|
--save_steps 1000 \
|
||
|
|
--learning_rate $LR \
|
||
|
|
--fp16
|
||
|
|
|