Qwen3-VL-8B-LoRA-ref-parsing

base_model: Qwen/Qwen3-VL-8B-Instruct
processor_type: AutoProcessor

# these 3 lines are needed for now to handle vision chat templates w images
skip_prepare_dataset: true
# remove_unused_columns: false
# sample_packing: false

chat_template: qwen2_vl

datasets:
  - path: yurui983/reference-parsing-finetuning
    split: train
    type: chat_template
    roles_to_train: [assistant]

test_datasets:
  - path: yurui983/reference-parsing-finetuning
    split: validation
    type: chat_template
    roles_to_train: [assistant]

dataset_prepared_path: last_run_prepared
output_dir: ./outputs/qwen3-vl-8b-out

adapter: lora
lora_model_dir:

sequence_len: 10000
excess_length_strategy: drop

lora_r: 64
lora_alpha: 128
lora_dropout: 0.1
lora_target_modules: 'model.language_model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'
# lora_target_linear: true  # Don't use this for vLM - it targets vision layers too

wandb_project: Qwen-lora-ref-parsing
wandb_entity: zhuyurui0323-odoma
wandb_watch: gradients
wandb_name: Qwen3-VL-8B-lora-ref-parsing
wandb_log_model: 'false'

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00005

bf16: auto
tf32: false

gradient_checkpointing: false
logging_steps: 5
flash_attention: true
eager_attention:

ddp_find_unused_parameters: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_ratio: 0.1
evals_per_epoch: 4
saves_per_epoch: 3
weight_decay: 0.0

max_grad_norm: 1.0

# Additional training stability settings
special_tokens:
  pad_token: "<|endoftext|>"

# save_first_step: true  # uncomment this to validate checkpoint saving works with your config