{
  "model": "openbmb/MiniCPM5-1B",
  "preset": "minicpm5-1b",
  "dataset": "/repo/research/data/education-lesson-chat.jsonl",
  "dataset_config": null,
  "dataset_split": "train",
  "mix": [
    {
      "dataset": "meta-math/MetaMathQA",
      "format": "prompt",
      "columns": {
        "prompt": "query",
        "response": "response"
      },
      "dataset_split": "train[:3000]",
      "max_samples": 3000
    },
    {
      "dataset": "tatsu-lab/alpaca",
      "format": "alpaca",
      "dataset_split": "train[:600]",
      "max_samples": 600
    }
  ],
  "format": "chat",
  "mode": "qlora",
  "output_dir": "/vol/finetuned/math-lora",
  "samples": {
    "train": 3528,
    "eval": 72
  },
  "metrics": {
    "final_train_loss": 0.340698,
    "eval_loss": 0.494981,
    "perplexity": 1.6405,
    "loss_score": 0.494981,
    "result_score": 60.96
  },
  "training": {
    "epochs": 1.0,
    "max_steps": 150,
    "global_step": 150,
    "train_runtime_sec": 310.98,
    "train_samples_per_second": 7.718
  }
}