Is there any examples to guide in llama3.2 vision lora or sft?

[moonlightian]

Reminder

• I have read the README and searched the existing issues.

System Info

None

Reproduction

None

Expected behavior

No response

Others

No response

[hiyouga]

### model
model_name_or_path: meta-llama/Llama-3.2-11B-Vision-Instruct
trust_remote_code: true

### method
stage: sft
do_train: true
finetuning_type: lora
lora_target: all

### dataset
dataset: mllm_demo
template: mllama
cutoff_len: 2048
max_samples: 1000
overwrite_cache: true
preprocessing_num_workers: 16

### output
output_dir: saves/llama_vision/lora/sft
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true

### train
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
learning_rate: 1.0e-4
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true
ddp_timeout: 180000000

### eval
val_size: 0.1
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 500