From 828d0599d73819ebde0f08959602fc656c25bb0f Mon Sep 17 00:00:00 2001 From: ruv Date: Fri, 3 Apr 2026 09:37:08 -0400 Subject: [PATCH] fix: skip triplet JSON export for large datasets (>100K) JSON.stringify fails on 1M+ triplets. Training succeeded (33.3% improvement) but export crashed. Now skips export when >100K triplets. Co-Authored-By: claude-flow --- scripts/train-ruvllm.js | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/scripts/train-ruvllm.js b/scripts/train-ruvllm.js index 77ebc4c2..93da640f 100644 --- a/scripts/train-ruvllm.js +++ b/scripts/train-ruvllm.js @@ -1257,9 +1257,13 @@ async function main() { contrastiveResult.finalLoss = finalContrastiveLoss; contrastiveResult.improvement = contrastiveImprovement; - // Export contrastive training data - const contrastiveOutDir = contrastiveTrainer.exportTrainingData(); - console.log(` Training data exported to: ${contrastiveOutDir}`); + // Export contrastive training data (skip for large datasets to avoid JSON string limit) + if (contrastiveTrainer.getTripletCount() < 100000) { + const contrastiveOutDir = contrastiveTrainer.exportTrainingData(); + console.log(` Training data exported to: ${contrastiveOutDir}`); + } else { + console.log(` Skipping triplet export (${contrastiveTrainer.getTripletCount()} triplets too large for JSON)`); + } // ----------------------------------------------------------------------- // Phase 2: Task head training via TrainingPipeline