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.
28 lines
833 B
28 lines
833 B
PRE_SEQ_LEN=128 |
|
LR=2e-2 |
|
NUM_GPUS=1 |
|
|
|
torchrun --standalone --nnodes=1 --nproc-per-node=$NUM_GPUS main.py \ |
|
--do_train \ |
|
--train_file AdvertiseGen/train.json \ |
|
--validation_file AdvertiseGen/dev.json \ |
|
--preprocessing_num_workers 10 \ |
|
--prompt_column content \ |
|
--response_column summary \ |
|
--overwrite_cache \ |
|
--model_name_or_path THUDM/chatglm2-6b \ |
|
--output_dir output/adgen-chatglm2-6b-pt-$PRE_SEQ_LEN-$LR \ |
|
--overwrite_output_dir \ |
|
--max_source_length 64 \ |
|
--max_target_length 128 \ |
|
--per_device_train_batch_size 1 \ |
|
--per_device_eval_batch_size 1 \ |
|
--gradient_accumulation_steps 16 \ |
|
--predict_with_generate \ |
|
--max_steps 3000 \ |
|
--logging_steps 10 \ |
|
--save_steps 1000 \ |
|
--learning_rate $LR \ |
|
--pre_seq_len $PRE_SEQ_LEN \ |
|
--quantization_bit 4 |
|
|
|
|