#!/usr/bin/env bash
set -euo pipefail
# Run from the package root in an existing compatible AMD ROCm environment.
# Replace these paths with your own isolated TRAIN and DEV JSONL files.
: "${TRAIN:?Set TRAIN to your training JSONL}"
: "${DEV:?Set DEV to your development JSONL}"
: "${OUTPUT:?Set OUTPUT to a fresh run directory}"
NATIVE="${NATIVE:-./native}"
MANIFEST_SHA256="${MANIFEST_SHA256:-f288d873999832a3f37c6a7c4268c2ab309691e621794dbf7acab891acbbb7e6}"
export PYTHONPATH="${PWD}${PYTHONPATH:+:${PYTHONPATH}}"
export PYTHONDONTWRITEBYTECODE=1 HF_HUB_OFFLINE=1 TRANSFORMERS_OFFLINE=1 TOKENIZERS_PARALLELISM=false
python -m decision_finetune validate-jsonl --train "$TRAIN" --dev "$DEV" --selection macro-nll
# Device visibility is supplied by the caller, e.g. ROCR_VISIBLE_DEVICES=0.
python -m decision_finetune train \
  --native "$NATIVE" --manifest-sha256 "$MANIFEST_SHA256" \
  --train "$TRAIN" --dev "$DEV" --output "$OUTPUT" \
  --epochs 4 --logical-batch-size 64 --micro-batch-size 8 --seed 20260921 \
  --encoder-lr 2.5e-5 --head-lr 1e-4 --lr-min 1e-6 \
  --weight-decay 0.01 --clip-norm 1 --score-rps-weight 0.1 \
  --warmup-ratio 0.1 --selection macro-nll --selection-tolerance 1e-8 \
  --cpu-threads 2 --max-reserved-gib 64