58 lines
1.3 KiB
YAML
58 lines
1.3 KiB
YAML
### Install model-specific dependencies: `pip install -r requirements/moss-vl.txt`
|
|
|
|
### model
|
|
model_name_or_path: OpenMOSS-Team/MOSS-VL-Instruct-0708
|
|
image_max_pixels: 262144
|
|
video_max_pixels: 16384
|
|
video_fps: 1.0
|
|
video_maxlen: 256
|
|
use_reentrant_gc: false
|
|
trust_remote_code: true
|
|
|
|
### method
|
|
stage: sft
|
|
do_train: true
|
|
finetuning_type: full
|
|
freeze_vision_tower: true
|
|
freeze_multi_modal_projector: true
|
|
freeze_language_model: false
|
|
deepspeed: examples/deepspeed/ds_z3_config.json
|
|
|
|
### dataset
|
|
dataset: mllm_demo,identity,alpaca_en_demo # video: mllm_video_demo
|
|
template: moss_vl
|
|
cutoff_len: 4096
|
|
max_samples: 1000
|
|
preprocessing_num_workers: 16
|
|
dataloader_num_workers: 4
|
|
packing: false
|
|
|
|
### output
|
|
output_dir: saves/moss-vl-11b/full/sft
|
|
logging_steps: 10
|
|
save_steps: 500
|
|
plot_loss: true
|
|
overwrite_output_dir: true
|
|
save_only_model: false
|
|
report_to: none # choices: [none, wandb, tensorboard, swanlab, mlflow]
|
|
|
|
### train
|
|
per_device_train_batch_size: 1
|
|
gradient_accumulation_steps: 1
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: false
|
|
learning_rate: 1.0e-5
|
|
num_train_epochs: 3.0
|
|
lr_scheduler_type: cosine
|
|
warmup_ratio: 0.1
|
|
bf16: true
|
|
ddp_timeout: 180000000
|
|
resume_from_checkpoint: null
|
|
|
|
### eval
|
|
# val_size: 0.1
|
|
# per_device_eval_batch_size: 1
|
|
# eval_strategy: steps
|
|
# eval_steps: 500
|