eval_report.json

{
  "overall": {
    "rows": 5053,
    "missed_calls": 4531
  },
  "overall_rates": {
    "tool_name_acc": 0.0,
    "strict_em": 0.0,
    "key_f1": 0.0,
    "missed_call_rate": 1.0,
    "false_call_rate": 0.0,
    "max_seq_len": 768,
    "base_model": "google/functiongemma-270m-it",
    "dataset": "metga97/arabic-tooluse-functiongemma-v1"
  }
}