{
  "compute_tier": "T4",
  "base_model": "unsloth/Qwen2.5-3B-bnb-4bit",
  "beta": 0.1,
  "lr": 5e-07,
  "epochs": 1,
  "final_train_loss": 0.7901351070404052,
  "end_chosen_reward": -0.699219024181366,
  "end_rejected_reward": -0.8914896249771118,
  "end_reward_gap": 0.19227060079574587
}