This adapter was trained for the StructEval competition using supervised fine-tuning (SFT).

unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit

RUN_ID: structeval_20260301_024851_32a2ac1e

Learning rate: 2.6e-6
Epochs: 2
Max seq length: 1536
Batch size: 2
Gradient accumulation: 4

LoRA: r = 64
alpha = 128
dropout = 0.0

Upsampling: {"toml": 3.0}

Validation loss: 0.9484043121337891

This LoRA adapter was trained to improve structured output generation (JSON / YAML / TOML / XML / CSV) for the StructEval competition.