training_stats.json

{
  "base_model": "Qwen/Qwen2.5-7B-Instruct",
  "dataset": "2reb/GameTheory-Bench",
  "train_examples": 2767,
  "eval_examples": 146,
  "lora_r": 64,
  "lora_alpha": 128,
  "epochs": 3,
  "batch_size": 2,
  "grad_accum": 8,
  "effective_batch": 16,
  "lr": 0.0002,
  "train_loss": 0.1613485331888552,
  "eval_loss": 0.08727391809225082,
  "runtime_seconds": 6895.8492
}