mirror of
https://github.com/OpenBMB/MiniCPM-V.git
synced 2026-02-04 17:59:18 +08:00
7e12387362
* update lora tuning * updata lora fine-tuning code * update finetuning lora code * lora code * lora finetuning code * updating lora finetuning code * update lora finetuning code * Update Lora finetuning code * Update LoRA finetuning code * Update LoRA finetuning code
62 lines
1.8 KiB
Bash
62 lines
1.8 KiB
Bash
#!/bin/bash
|
|
|
|
GPUS_PER_NODE=8
|
|
NNODES=1
|
|
NODE_RANK=0
|
|
MASTER_ADDR=localhost
|
|
MASTER_PORT=6001
|
|
|
|
MODEL="openbmb/MiniCPM-Llama3-V-2_5" # or openbmb/MiniCPM-V-2
|
|
# ATTENTION: specify the path to your training data, which should be a json file consisting of a list of conversations.
|
|
# See the section for finetuning in README for more information.
|
|
DATA="path/to/trainging_data"
|
|
EVAL_DATA="path/to/test_data"
|
|
LLM_TYPE="llama3" # if use openbmb/MiniCPM-V-2, please set LLM_TYPE=minicpm
|
|
|
|
DISTRIBUTED_ARGS="
|
|
--nproc_per_node $GPUS_PER_NODE \
|
|
--nnodes $NNODES \
|
|
--node_rank $NODE_RANK \
|
|
--master_addr $MASTER_ADDR \
|
|
--master_port $MASTER_PORT
|
|
"
|
|
torchrun $DISTRIBUTED_ARGS finetune.py \
|
|
--model_name_or_path $MODEL \
|
|
--llm_type $LLM_TYPE \
|
|
--data_path $DATA \
|
|
--eval_data_path $EVAL_DATA \
|
|
--remove_unused_columns false \
|
|
--label_names "labels" \
|
|
--prediction_loss_only false \
|
|
--bf16 true \
|
|
--bf16_full_eval true \
|
|
--do_train \
|
|
--do_eval \
|
|
--tune_vision false \
|
|
--tune_llm false \
|
|
--use_lora true \
|
|
--lora_target_modules "llm\..*layers\.\d+\.self_attn\.(q_proj|k_proj)" \
|
|
--model_max_length 2048 \
|
|
--max_steps 10000 \
|
|
--eval_steps 1000 \
|
|
--output_dir output/output_minicpmv2_lora \
|
|
--logging_dir output/output_minicpmv2_lora \
|
|
--logging_strategy "steps" \
|
|
--per_device_train_batch_size w \
|
|
--per_device_eval_batch_size 1 \
|
|
--gradient_accumulation_steps 1 \
|
|
--evaluation_strategy "steps" \
|
|
--save_strategy "steps" \
|
|
--save_steps 1000 \
|
|
--save_total_limit 10 \
|
|
--learning_rate 1e-6 \
|
|
--weight_decay 0.1 \
|
|
--adam_beta2 0.95 \
|
|
--warmup_ratio 0.01 \
|
|
--lr_scheduler_type "cosine" \
|
|
--logging_steps 1 \
|
|
--gradient_checkpointing true \
|
|
--deepspeed ds_config_zero2.json \
|
|
--report_to "tensorboard" \ # wandb
|
|
|