rlvrif-qwen2.5-1.5b/eval-results/human-eval/metrics.json

{
  "human-eval": {
    "pass@1": {
      "num_entries": 164,
      "avg_tokens": 98,
      "gen_seconds": 20,
      "passing_base_tests": 44.51219512195122,
      "passing_plus_tests": 38.41463414634146
    }
  }
}