configs/m2_large.yaml

# Optimized config for M2 Mac with 50k-500k samples
# Training time: ~2-8 hours (depending on size)
# Use only if you need maximum performance
data_path: data/dataset.csv
base_model: roberta-base
save_dir: models/ai_detector

max_length: 256
batch_size: 4   # Smaller batch to fit in memory
num_epochs: 2
lr: 5e-5
weight_decay: 0.01
logging_steps: 100
eval_strategy: steps
eval_steps: 500  # Evaluate more frequently
seed: 42
gradient_accumulation_steps: 4  # Effective batch size = 16
fp16: false
warmup_ratio: 0.1
save_total_limit: 2
save_steps: 0
dataloader_num_workers: 0  # macOS requires 0 to avoid threading issues