benchmarks.json

{
  "yc_bench_oneshot": {
    "base": {
      "avg_composite_score": 0.5509199735446368,
      "survival_rate": 1.0,
      "evaluation_time_seconds": 78.61562085151672
    },
    "merged": {
      "avg_composite_score": 0.5509199735446368,
      "survival_rate": 1.0,
      "evaluation_time_seconds": 23.148362159729004
    },
    "delta": {
      "avg_composite_score": 0.0,
      "survival_rate": 0.0,
      "evaluation_time_seconds": -55.46725869178772,
      "speedup_x": 3.396,
      "time_reduction_pct": 70.6
    }
  },
  "training_progression": {
    "stage_a_eval_loss": 0.4059831202030182,
    "stage_b_eval_loss": 0.3007583022117615,
    "stage_a_eval_perplexity": 1.5007772194294333,
    "stage_b_eval_perplexity": 1.3508827966928918
  }
}