mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-07-23 04:21:14 +08:00
42458914c8
* support dora finetune * solve problems in lora.py and tuner.utils.py * add use_dora (bool) in functions of load adapters * delete all unsupported quantization code and fix all the calculate problems in mlx_lm/tuner/dora.py * Using stop_gradient to prevent gradients from flowing through ‘norm’ during backpropagation * set DEFAULT_USE_DORA in mlx_lm/generate.py * add annotation for all the use_dora * mlx_lm/fuse.py support fuse dora layers and fix a bug of to_linear() in mlx_lm/tuner/dora.py * simplify code of juding type of a fused layer in mlx_lm/fuse.py * add use_dora in mlx_lm/fuse.py when apply_lora_layers() * style + nits * style + nits * more updates --------- Co-authored-by: chenyifei08 <chenyifei08@baidu.com> Co-authored-by: Awni Hannun <awni@apple.com>
73 lines
1.6 KiB
YAML
73 lines
1.6 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: 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
|
|
|
|
# Use DoRA instead of LoRA.
|
|
use_dora: 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
|
|
alpha: 16.0
|
|
scale: 10.0
|
|
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
|