# The path to the local model directory or Hugging Face repo.
model: "mlx_model"

# Whether or not to train (boolean)
train: true

# The fine-tuning method: "lora", "dora", or "full".
fine_tune_type: lora

# Directory with {train, valid, test}.jsonl files
data: "/path/to/training/data"

# The PRNG seed
seed: 0

# Number of layers to fine-tune
num_layers: 16

# Minibatch size.
batch_size: 4

# Iterations to train for.
iters: 1000

# Number of validation batches, -1 uses the entire validation set.
val_batches: 25

# Adam learning rate.
learning_rate: 1e-5

# Number of training steps between loss reporting.
steps_per_report: 10

# Number of training steps between validations.
steps_per_eval: 200

# Load path to resume training with the given adapter weights.
resume_adapter_file: null

# Save/load path for the trained adapter weights.
adapter_path: "adapters"

# Save the model every N iterations.
save_every: 100

# Evaluate on the test set after training
test: false

# Number of test set batches, -1 uses the entire test set.
test_batches: 100

# Maximum sequence length.
max_seq_length: 2048

# Use gradient checkpointing to reduce memory use.
grad_checkpoint: false

# LoRA parameters can only be specified in a config file
lora_parameters:
  # The layer keys to apply LoRA to.
  # These will be applied for the last lora_layers
  keys: ["self_attn.q_proj", "self_attn.v_proj"]
  rank: 8
  scale: 20.0
  dropout: 0.0

# Schedule can only be specified in a config file, uncomment to use.
#lr_schedule:
#  name: cosine_decay
#  warmup: 100 # 0 for no warmup
#  warmup_init: 1e-7 # 0 if not specified
#  arguments: [1e-5, 1000, 1e-7] # passed to scheduler

#hf_dataset:
#  name: "billsum"
#  train_split: "train[:1000]"
#  valid_split: "train[-100:]"
#  prompt_feature: "text"
#  completion_feature: "summary"