| PRE_SEQ_LEN=128 | |
| LR=1e-2 | |
| NUM_GPUS=1 | |
| torchrun --standalone --nnodes=1 --nproc-per-node=$NUM_GPUS ptuning/main.py \ | |
| --do_train \ | |
| --train_file train.json \ | |
| --validation_file dev.json \ | |
| --preprocessing_num_workers 10 \ | |
| --prompt_column content \ | |
| --response_column summary \ | |
| --history_column history \ | |
| --overwrite_cache \ | |
| --model_name_or_path chatglm2-6b \ | |
| --output_dir output_model \ | |
| --overwrite_output_dir \ | |
| --max_source_length 256 \ | |
| --max_target_length 256 \ | |
| --per_device_train_batch_size 1 \ | |
| --per_device_eval_batch_size 1 \ | |
| --gradient_accumulation_steps 16 \ | |
| --predict_with_generate \ | |
| --max_steps 200 \ | |
| --logging_steps 10 \ | |
| --save_steps 100 \ | |
| --learning_rate $LR \ | |
| --pre_seq_len $PRE_SEQ_LEN | |