evals/cap_base.json

{
  "model": "google/gemma-2-2b-it",
  "scores": {
    "MMLU": 0.5438678813269133,
    "Hellaswag": 0.7035194514978154,
    "Arc": 0.5978744623708486,
    "Winogrande": 0.6683725258470004,
    "TruthfulQA": 0.5215722198239925,
    "GSM8k": 0.5756843365020538
  },
  "avg": 0.6018
}