# Stage 1 short test: 20 iterations, same settings as config.yaml. Run: MLX_DISABLE_COMPILE=1 train/.venv/bin/mlx_lm.lora -c train/config_test.yaml
model: /Users/erhankeseli/models/Qwen3.8-27B-4bit
train: true
data: train/data
fine_tune_type: lora
num_layers: -1
lora_parameters:
  rank: 16
  scale: 20.0
  dropout: 0.0
batch_size: 1
grad_checkpoint: true
iters: 20
learning_rate: 5.0e-5
lr_schedule:
  name: cosine_decay
  warmup: 2
  arguments: [5.0e-5, 20, 0.0]
max_seq_length: 16384
steps_per_report: 1
steps_per_eval: 20
val_batches: 3
save_every: 20
adapter_path: train/adapters_test
seed: 20261003