qwen3-4b-structured-output-lora-v6

qwen3-4b-structured-output-lora-v6

This repository provides a LoRA adapter (v5.2) fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using QLoRA (4-bit, Unsloth).

This repository contains LoRA adapter weights only. The base model must be loaded separately.

Version: v5.2 — Hyperparameter Tuning

This is v5.2 of the SFT training, focusing on hyperparameter tuning to address overfitting in v5. v5 achieved 0.73981, which was lower than v2 (0.75074) due to Epoch=2 causing overfitting.

Changes from v5

v5.2 Key Improvements

1. Epoch=1: v5's Epoch=2 caused overfitting (train/loss increased at end)
2. Learning Rate 5e-6: More conservative learning to prevent overfitting
3. Warmup Ratio 10%: Longer warmup for training stability
4. Data unchanged: 3,869 samples with XML errors removed

Score History

Training Objective

This adapter is trained to improve structured output accuracy (JSON / YAML / XML / TOML / CSV) for the StructEval-T benchmark.

Loss is applied only to the final assistant output, while intermediate reasoning (Chain-of-Thought) is masked.

Training Configuration

• Base model: Qwen/Qwen3-4B-Instruct-2507
• Method: QLoRA (4-bit, Unsloth)
• Max sequence length: 1024
• Epochs: 1
• Learning rate: 1e-06
• Warmup ratio: 10%
• Batch size: 2 (effective: 16)
• Gradient accumulation: 8
• LoRA: r=64, alpha=128
• CoT masking: enabled (loss on final output only)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base = "Qwen/Qwen3-4B-Instruct-2507"
adapter = "your_id/qwen3-4b-structured-output-lora-v6"

tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(
    base,
    torch_dtype=torch.float16,
    device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter)

Sources & Terms (IMPORTANT)

Training data: u-10bei/structured_data_with_cot_dataset_512_v2

Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License. Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.