|
|
base_model: Qwen/Qwen2.5-VL-7B-Instruct |
|
|
processor_type: AutoProcessor |
|
|
|
|
|
|
|
|
skip_prepare_dataset: true |
|
|
remove_unused_columns: false |
|
|
sample_packing: false |
|
|
|
|
|
chat_template: qwen2_vl |
|
|
datasets: |
|
|
- path: sanskrit_multimodal_train.json |
|
|
type: chat_template |
|
|
field_messages: messages |
|
|
dataset_prepared_path: last_run_prepared |
|
|
val_set_size: 0.01 |
|
|
output_dir: ./outputs/out-qwen2-5-vl |
|
|
|
|
|
adapter: lora |
|
|
lora_model_dir: |
|
|
|
|
|
sequence_len: 2048 |
|
|
pad_to_sequence_len: false |
|
|
|
|
|
lora_r: 32 |
|
|
lora_alpha: 16 |
|
|
lora_dropout: 0.05 |
|
|
lora_target_modules: 'model.language_model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj' |
|
|
|
|
|
wandb_project: Sanskrit-OCR |
|
|
wandb_entity: |
|
|
wandb_watch: |
|
|
wandb_name: qwen2-5-vl-sanskrit-ocr |
|
|
wandb_log_model: |
|
|
|
|
|
gradient_accumulation_steps: 4 |
|
|
micro_batch_size: 2 |
|
|
num_epochs: 3 |
|
|
optimizer: adamw_bnb_8bit |
|
|
lr_scheduler: cosine |
|
|
learning_rate: 0.0002 |
|
|
|
|
|
bf16: true |
|
|
fp16: |
|
|
tf32: true |
|
|
|
|
|
gradient_checkpointing: true |
|
|
logging_steps: 1 |
|
|
flash_attention: true |
|
|
eager_attention: |
|
|
|
|
|
warmup_ratio: 0.1 |
|
|
evals_per_epoch: 1 |
|
|
saves_per_epoch: 1 |
|
|
weight_decay: 0.0 |
|
|
|
|
|
|
|
|
hub_model_id: diabolic6045/qwen2-5-vl-sanskrit-ocr-lora |
|
|
|
