#!/usr/bin/env bash set -eo pipefail SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" # shellcheck disable=SC1091 source "${SCRIPT_DIR}/conda_env.sh" set -u REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)" cd "${REPO_ROOT}" export PYTHONPATH="${REPO_ROOT}/src" export WANDB_DIR="${WANDB_DIR:-${REPO_ROOT}/cache/logs/wandb}" export WANDB_MODE="${WANDB_MODE:-offline}" export HF_HUB_OFFLINE="${HF_HUB_OFFLINE:-1}" export HF_DATASETS_OFFLINE="${HF_DATASETS_OFFLINE:-1}" export TRANSFORMERS_OFFLINE="${TRANSFORMERS_OFFLINE:-1}" accelerate launch \ --config_file configs/accelerate_ddp_2gpu.yaml \ src/train_grpo.py \ --config configs/grpo_llama32_3b_bf16.yaml