base_model: alpindale/Llama-3.2-11B-Vision-Instruct
# optionally might have model_type or tokenizer_type or processor_type
processor_type: AutoProcessor
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name


# 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: llama3_2_vision
datasets:
  - path: HuggingFaceH4/llava-instruct-mix-vsft
    type: chat_template
    split: train[:1%]
    field_messages: messages
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./outputs/out

adapter: lora
lora_model_dir:

sequence_len: 8192
pad_to_sequence_len: false

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules: 'language_model.model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 1
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