mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-07-03 07:11:13 +08:00
8c2cf665ed
* Convert mlx_lm.lora to use YAML configuration * pre-commit run fixes * Fix loading of config file * Remove invalid YAML from doc * Update command-line options and YAML parameter overriding, per feedback in #503 * Minor wording change * Positional argument * Moved config to a (-c/--config) flag * Removed CLI option defaults (since CLI options take precedence and their defaults are in CONFIG_DEFAULTS) * pre-commit format updates * Fix handling of CLI option defaults * Prevent None values of unspecified CLI options from overwriting values from CONFIG_DEFAULTS * nits --------- Co-authored-by: Awni Hannun <awni@apple.com>
51 lines
1.0 KiB
YAML
51 lines
1.0 KiB
YAML
# The path to the local model directory or Hugging Face repo.
|
|
model: "mlx_model"
|
|
|
|
# Whether or not to train (boolean)
|
|
train: true
|
|
|
|
# Directory with {train, valid, test}.jsonl files
|
|
data: "/path/to/training/data"
|
|
|
|
# The PRNG seed
|
|
seed: 0
|
|
|
|
# Number of layers to fine-tune
|
|
lora_layers: 16
|
|
|
|
# Minibatch size.
|
|
batch_size: 4
|
|
|
|
# Iterations to train for.
|
|
iters: 100
|
|
|
|
# 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_file: "adapters.npz"
|
|
|
|
# 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: 500
|
|
|
|
# Maximum sequence length.
|
|
max_seq_length: 2048
|