configs/m2_small.yaml

# Optimized config for M2 Mac with 1k-10k samples
# Training time: ~5-15 minutes
data_path: data/dataset.csv
base_model: roberta-base
save_dir: models/ai_detector

max_length: 256
batch_size: 16  # Larger batch for smaller dataset
num_epochs: 3   # More epochs since dataset is smaller
lr: 5e-5
weight_decay: 0.01
logging_steps: 10
eval_strategy: epoch
seed: 42
gradient_accumulation_steps: 1
fp16: false  # M2 Mac doesn't have CUDA, so no FP16
warmup_ratio: 0.1  # Add warmup for stability
save_total_limit: 2
save_steps: 0
dataloader_num_workers: 0  # macOS requires 0 to avoid threading issues