base_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503
processor_type: AutoProcessor

# Enable to use mistral-common tokenizer
tokenizer_use_mistral_common: true

load_in_8bit: true

# 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

# sample dataset below requires downloading image in advance
# wget https://huggingface.co/datasets/Nanobit/text-vision-2k-test/resolve/main/African_elephant.jpg
datasets:
  - path: Nanobit/text-vision-2k-test
    type: chat_template

dataset_prepared_path: last_run_prepared
val_set_size: 0.01
output_dir: ./outputs/out

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:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 2
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

warmup_ratio: 0.1
evals_per_epoch: 1
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:

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