sudo apt update && sudo apt upgrade -y && sudo apt autoremove -y \
&& sudo apt install -y docker.io pwgen jq joe screen \
&& sudo reboot
Now run screen and inside
| # train_grpo.py | |
| # | |
| # See https://github.com/willccbb/verifiers for ongoing developments | |
| # | |
| import re | |
| import torch | |
| from datasets import load_dataset, Dataset | |
| from transformers import AutoTokenizer, AutoModelForCausalLM | |
| from peft import LoraConfig | |
| from trl import GRPOConfig, GRPOTrainer |