From 6ba963aca3a4e5de04b5a3282c998ea072ff16a2 Mon Sep 17 00:00:00 2001 From: thinhlpg Date: Mon, 14 Apr 2025 06:31:23 +0000 Subject: [PATCH] feat: streamline data preparation in Makefile with a single command --- Makefile | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/Makefile b/Makefile index 85c34f3..1ef67cf 100644 --- a/Makefile +++ b/Makefile @@ -37,9 +37,9 @@ list-runs: @echo "Available run directories:" @ls -d trainer_output_*_runs 2>/dev/null || echo "No run directories found" -# Data Preparation -data: prepare-musique-jsonl - @echo "Data preparation complete." +# Data Preparation - One command to rule them all +data: download-musique prepare-musique-jsonl extract-musique-paragraphs build-musique-index prepare-dev-data check-data + @echo "✨ All data preparation complete! ✨" # Index Preparation prepare-musique-index: build-musique-index @@ -70,7 +70,7 @@ prepare-all-musique: data prepare-musique-index @echo "All Musique data and index preparation complete." # Check Data -check-data: prepare-all-musique prepare-dev-data +check-data: @echo "Checking generated data files..." python scripts/check_data.py