| # Reproduces the fine-tuning run behind the submitted model. | |
| # | |
| # bash run_training.sh [out_dir] | |
| # | |
| # Needs: one 48 GB GPU (reference: NVIDIA A40), ~17 GB disk for the base weights. | |
| # Runtime on the reference machine: 88 minutes, peak VRAM 28.0 GB. | |
| # | |
| # The SFT files are published at: | |
| # https://huggingface.co/datasets/QBitsLK/sinhala-mcq-sft-v3 | |
| # and are downloaded here. run_data_pipeline.sh rebuilds them from the raw extractions. | |
| set -euo pipefail | |
| OUT_DIR="${1:-/workspace/outputs/mcq_sft_cpt_v3}" | |
| BASE_MODEL="QBitsLK/gemma4-e4b-sinhala-cpt" | |
| DATA_REPO="QBitsLK/sinhala-mcq-sft-v3" | |
| hf download "$DATA_REPO" --repo-type dataset --local-dir ./sft_data | |
| TRAIN=./sft_data/sft_train3.jsonl | |
| VAL=./sft_data/sft_val3.jsonl | |
| wc -l "$TRAIN" "$VAL" # expect 21235 and 721 | |
| python sft_gemma4_mcq.py \ | |
| --train "$TRAIN" --val "$VAL" \ | |
| --model "$BASE_MODEL" \ | |
| --out "$OUT_DIR" \ | |
| --lora_r 32 --lora_alpha 32 --lr 1e-4 \ | |
| --epochs 2 --batch_size 8 --grad_accum 4 \ | |
| --max_seq_length 1024 --warmup_steps 10 \ | |
| --eval_steps 150 --seed 3407 | |
| echo | |
| echo "== the submitted checkpoint is $OUT_DIR/final_adapter (step 1328), NOT best_adapter." | |
| echo "== see SYSTEM_DESCRIPTION.md section 5.2 for why." | |