frank/ruvnet--RuView
1
0
Fork 0
mirror of https://github.com/ruvnet/RuView synced 2026-07-24 17:43:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #356 from ruvnet/fix/large-dataset-training

Browse Source 
fix: skip triplet JSON export for large datasets (>100K)
This commit is contained in:
rUv
2026-04-03 09:37:30 -04:00
committed by GitHub
parent 21fd7c84e2 828d0599d7
commit aae01a2be8
1 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/train-ruvllm.js
+7 -3
View File
@@ -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