Cyber_analyst-round1 / scripts /modal_run_ephemeral.sh
Humanlearning's picture
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts.
3807ea3
raw
history blame
165 Bytes
#!/usr/bin/env bash
set -euo pipefail
modal run scripts/modal_ephemeral_train.py --mode "${MODE:-smoke}" --episodes "${EPISODES:-4}" --seed-start "${SEED_START:-0}"