#!/usr/bin/env sh
# Cross-eval: trained on tri (native_tool_response_only) -> evaluate on squad. model=Qwen3-4B
set -eu

SCRIPT_DIR=$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)
EVAL_DIR=$(CDPATH= cd -- "$SCRIPT_DIR/.." && pwd)
BASE=$(CDPATH= cd -- "$EVAL_DIR/.." && pwd)
ROOT=$(CDPATH= cd -- "$BASE/.." && pwd)

export MODEL_PATH="${MODEL_PATH:-$ROOT/models/Qwen3-4B}"
export LORA_PATH="${LORA_PATH:-$BASE/3-2_model_training/outputs_lora/qwen3-4b_tri_nts_all_roc_inst_0.1/final}"
export EVAL_DATA_PATH="${EVAL_DATA_PATH:-$BASE/1_raw_dataset/topicattack/data/crafted_instruction_data_squad_injection_qa.json}"
export EVAL_TOPIC_PATH="${EVAL_TOPIC_PATH:-$BASE/1_raw_dataset/topicattack/data/crafted_instruction_data_squad_conversation_attack_complete.json}"
export EVAL_CONFIG="${EVAL_CONFIG:-native_tool_response_only}"
export EVAL_OUTPUT="${EVAL_OUTPUT:-$EVAL_DIR/results/qwen3-4b_tritrain_squadeval_nts.json}"

exec "$EVAL_DIR/eval_single.sh"