metadata
base_model: Qwen/Qwen3-4B-Instruct-2507
datasets:
- u-10bei/structured_data_with_cot_dataset_512_v2
language:
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- sft
- structured-output
- qwen3
qwen3-4b-structeval-v13
V11-base + seed=42 only change.
- lr=1.5e-05, epochs=2, r=8, alpha=8, BS=32
- dropout=0, seed=42
- enable_thinking=False, strip_cot=True(strict)