### model
model_name_or_path: /home/zbz5349/WorkSpace/aigeeks/Qwen2.5-VL/ckpt
image_max_pixels: 262144
video_max_pixels: 16384
trust_remote_code: true

### method
stage: sft
do_train: true
finetuning_type: lora
lora_rank: 8
lora_target: all

### dataset
dataset: Percption
template: qwen2_vl
cutoff_len: 2048
max_samples: 1000
overwrite_cache: true
preprocessing_num_workers: 16

### output
output_dir: results/Qwen2.5-VL-3B_all
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