{
  "base_model": "kmseong/Llama-3.1-8B-base-SSFT_lr5e-5",
  "fine_tuning_type": "Full Parameter Fine-tuning",
  "dataset": "GSM8K",
  "num_train_samples": 7473,
  "batch_size": 4,
  "grad_accum": 4,
  "learning_rate": 1e-05,
  "weight_decay": 0.01,
  "warmup_ratio": 0.1,
  "epochs": 3,
  "max_length": 1024,
  "max_grad_norm": 1.0,
  "lr_scheduler_type": "cosine",
  "optimizer": "AdamW (torch)",
  "gradient_checkpointing": false,
  "dtype": "bf16",
  "trainer_type": "Trainer",
  "safety_mix_ratio": 0.0,
  "safety_data_path": null
}