| license: other | |
| tags: | |
| - high-energy-physics | |
| - hep | |
| - verl | |
| - qwen2.5 | |
| - fine-tuning | |
| # HEP Posttraining | |
| This repository contains the training, data preparation, evaluation, and plotting setup used for HEP-focused post-training experiments. | |
| ## Main Workflows | |
| - Generate and validate signature-background datasets. | |
| - Prepare VERL SFT and RL parquet data. | |
| - Launch Qwen2.5 SFT and RL/GRPO experiments. | |
| - Export VERL checkpoints to Hugging Face format. | |
| - Evaluate checkpoint losses and decoded validation generations. | |
| ## Published Artifacts | |
| - Model: `ho22joshua/hep-qwen2.5-7b-lora16-sigbg-irred-red-step2200` | |
| - Dataset: `ho22joshua/hep-signature-backgrounds` | |
| ## Basic Usage | |
| ```bash | |
| python dataset/scripts/generate_signature_background_dataset.py | |
| python dataset/scripts/validate_dataset.py | |
| python dataset/scripts/prepare_verl_sft.py | |
| python dataset/scripts/prepare_verl_rl.py | |
| ``` | |
| For VERL training, see the command templates in `README.md`. | |
| ## Notes | |
| Large generated files such as checkpoints, local datasets, downloaded PDFs, caches, and logs are intentionally excluded from this code repository. | |