Upload start_training.sh with huggingface_hub

start_training.sh

@@ -0,0 +1,50 @@
+#!/bin/bash
+# Start CodeLlama fine-tuning with optimized hyperparameters
+
+cd /workspace/ftt/codellama-migration
+
+BASE_MODEL="/workspace/ftt/codellama-migration/models/base-models/CodeLlama-7B-Instruct"
+DATASET="datasets/processed/split/train.jsonl"
+OUTPUT_DIR="training-outputs/codellama-fifo-v1"
+
+echo "======================================================================"
+echo "🚀 Starting CodeLlama Fine-Tuning"
+echo "======================================================================"
+echo "Base Model: $BASE_MODEL"
+echo "Dataset: $DATASET"
+echo "Output: $OUTPUT_DIR"
+echo "======================================================================"
+
+# Create output directory
+mkdir -p "$OUTPUT_DIR"
+
+# Activate virtual environment if needed
+if [ -f /venv/main/bin/activate ]; then
+    source /venv/main/bin/activate
+fi
+
+# Start training with optimized hyperparameters
+python3 scripts/training/finetune_codellama.py \
+    --base-model "$BASE_MODEL" \
+    --dataset "$DATASET" \
+    --output-dir "$OUTPUT_DIR" \
+    --resume-from-checkpoint auto \
+    --max-length 1536 \
+    --num-epochs 5 \
+    --batch-size 2 \
+    --gradient-accumulation 4 \
+    --learning-rate 2e-5 \
+    --lora-r 48 \
+    --lora-alpha 96 \
+    --lora-dropout 0.15 \
+    --warmup-ratio 0.1 \
+    --eval-steps 25 \
+    --save-steps 25 \
+    --early-stopping-patience 5 \
+    --logging-steps 5
+
+echo ""
+echo "======================================================================"
+echo "✅ Training Complete!"
+echo "======================================================================"
+