matsuo-llm-advanced-phase-e6a

Fine-tuned from Qwen/Qwen2.5-7B-Instruct for agent tasks.

Training Configuration

• LoRA: r=12, alpha=24 (r=8→12 only change from Phase D)
• lr: 1e-5, epochs: 0.3, batch: 4×4=16
• Data: Phase D identical (Spider/BIRD 70% + DBBench 20% + ALFWorld 10%, 3500 samples)

Datasets

• u-10bei/dbbench_sft_dataset_react_v4 — Listed in the organizer-shared Phase B dataset list. Used as provided (no modification). Third-party synthetic SFT for DBBench format alignment; all tables, data, and queries are independently generated (per dataset description: "to avoid test data leakage").
• xlangai/spider — CC BY-SA 4.0 (Yale/Columbia Spider project)
• birdsql/bird_mini_dev — CC BY-SA 4.0 (HKU)
• Official Phase B ALFWorld v5 dataset — Organizer-provided, used as provided.

Compliance

• Evaluation data not used in training: No analysis of evaluation test data was conducted.
• LLM was not used for data quality filtering or selection.
• Inference code not modified.

Usage

Compatible with vLLM v0.13.0+.