configs/orpo_3b_1gpu.yaml

# EVAFRILL-Mo 3B ORPO — Single GPU (H100 MIG 3g.40gb, 42.3GB VRAM)
#
# Base model: checkpoints/3b_final/checkpoint-0319772 (Pretrained, NOT SFT)
# Method: ORPO (SFT + Odds Ratio Preference) with LoRA
#
# [설계 근거]
#   - ORPO는 SFT+정렬을 동시에 학습 → pretrained 모델에서 시작
#   - Reference model 불필요 → DPO보다 VRAM 절약
#   - LoRA rank=32: base(6GB) + LoRA(0.3GB) + optim(0.2GB) + act(~8GB) ≈ 15GB
#   - eff_batch: 1 × 16 grad_accum = 16

train:
  max_steps: 10000
  batch_size: 1
  grad_accum_steps: 16
  lr: 5.0e-6
  weight_decay: 0.01
  warmup_steps: 500
  max_length: 1024
  lambda_or: 1.0

  use_lora: true
  lora_rank: 32
  lora_alpha: 64

  save_interval: 1000
  log_interval: 10