Commit 9f69dd10 authored by zhaoying1's avatar zhaoying1
Browse files

Delete pt_train.sh

parent 85b2678e
PRE_SEQ_LEN=128
LR=5e-3
MASTER_PORT=$(shuf -n 1 -i 10000-65535)
CUDA_VISIBLE_DEVICES=0,1,2,3 deepspeed --master_port $MASTER_PORT main.py \
--deepspeed deepspeed.json \
--do_train \
--train_file AdvertiseGen/train.json \
--test_file AdvertiseGen/dev.json \
--prompt_column content \
--response_column summary \
--overwrite_cache \
--model_name_or_path THUDM/chatglm-6b \
--output_dir ./output_pt/adgen-chatglm-6b-pt-4c-$LR \
--overwrite_output_dir \
--max_source_length 64 \
--max_target_length 64 \
--per_device_train_batch_size 16 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 1 \
--predict_with_generate \
--max_steps 3000 \
--logging_steps 10 \
--save_steps 1000 \
--learning_rate $LR \
--pre_seq_len $PRE_SEQ_LEN \
--fp16
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment