File size: 2,105 Bytes
569f484
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
#!/bin/bash

GPUS_PER_NODE=8
NNODES=1
NODE_RANK=0
MASTER_ADDR=localhost
MASTER_PORT=6001

MODEL="openbmb/MiniCPM-V-2_6" # or openbmb/MiniCPM-V-2, openbmb/MiniCPM-Llama3-V-2_5
# 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="qwen2" 
# if use openbmb/MiniCPM-V-2, please set LLM_TYPE=minicpm
#if use openbmb/MiniCPM-Llama3-V-2_5, please set LLM_TYPE=llama3

MODEL_MAX_Length=2048 # if conduct multi-images sft, please set MODEL_MAX_Length=4096

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 false \
    --bf16_full_eval false \
    --fp16 true \
    --fp16_full_eval true \
    --do_train \
    --do_eval \
    --tune_vision true \
    --tune_llm false \
    --use_lora true \
    --lora_target_modules "llm\..*layers\.\d+\.self_attn\.(q_proj|k_proj|v_proj|o_proj)" \
    --model_max_length $MODEL_MAX_Length \
    --max_slice_nums 9 \
    --max_steps 10000 \
    --eval_steps 1000 \
    --output_dir output/output__lora \
    --logging_dir output/output_lora \
    --logging_strategy "steps" \
    --per_device_train_batch_size 1 \
    --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