training-scripts / README.md
passagereptile455's picture
Update README for cleaned repo
1ded106 verified
metadata
tags:
  - fine-tuning
  - lora
  - humaneval
  - qwen3
license: apache-2.0

Training Scripts

Fine-tuning script for reproducing the HuggingFace fine-tuning challenge.

Script

train_humaneval_clean.py - Fine-tune Qwen3-0.6B to beat base on HumanEval.

Usage

hf jobs uv run   --flavor a10g-small   --timeout 14400   --secrets HF_TOKEN   "https://huggingface.co/passagereptile455/training-scripts/resolve/main/train_humaneval_clean.py"

Results

See qwen3-humaneval-sft for the trained model and full results.

Notes

Script uses PEP 723 inline dependencies - no local setup required.