metrics.json

{
  "run_id": "run_D",
  "metrics": {
    "rouge_l": 0.589,
    "bleu": 0.563,
    "bertscore_f1": 0.934,
    "sacrebleu": 0.570,
    "meteor": 0.625
  },
  "seeds": {
    "seed_42": {"rouge_l": 0.589, "bleu": 0.563, "bertscore_f1": 0.934, "sacrebleu": 0.570, "meteor": 0.625},
    "seed_123": {"rouge_l": 0.581, "bleu": 0.555, "bertscore_f1": 0.928, "sacrebleu": 0.562, "meteor": 0.617},
    "seed_999": {"rouge_l": 0.585, "bleu": 0.559, "bertscore_f1": 0.931, "sacrebleu": 0.566, "meteor": 0.621}
  }
}