first commit

Codes/4_model_evaluation/lib/Ident_verb_test_dataset.sh

@@ -0,0 +1,100 @@
+#!/bin/bash
+set -euo pipefail
+
+CONDA_BIN=${CONDA_BIN:-}
+if [ -z "$CONDA_BIN" ]; then
+  if command -v conda >/dev/null 2>&1; then
+    CONDA_BIN=$(command -v conda)
+  elif [ -x /opt/miniconda/bin/conda ]; then
+    CONDA_BIN=/opt/miniconda/bin/conda
+  fi
+fi
+
+if [ -n "$CONDA_BIN" ]; then
+  eval "$("$CONDA_BIN" shell.bash hook)"
+  conda activate focallora
+else
+  echo "[Ident_verb_test_dataset.sh] Warning: conda not found; running in current environment." >&2
+fi
+
+SCRIPT_DIR="$(cd -- "$(dirname "$0")" && pwd)"
+export PYTHONPATH="$SCRIPT_DIR${PYTHONPATH:+:$PYTHONPATH}"
+export IGNORE_REASONING_MESSAGES="${IGNORE_REASONING_MESSAGES:-1}"
+
+TRAJ_PATH="${TRAJ_PATH:-/data/local/hujk/BUTTON/crafted_data/attack_dh_traj.jsonl}"
+TOKENIZER_PATH="${TOKENIZER_PATH:-/data/local/hujk/models/Qwen3-8B}"
+
+python3 - <<'PY'
+import json
+import os
+from pathlib import Path
+from transformers import AutoTokenizer
+from lib_tokenize_data_mask import (
+    apply_chat_with_tokenize_with_mark,
+    apply_chat_with_tokenize_original,
+    filter_reasoning_messages,
+    is_ignore_reasoning_enabled,
+    strip_markers,
+)
+
+traj_path = Path(os.getenv("TRAJ_PATH", "/data/local/hujk/BUTTON/crafted_data/attack_dh_traj.jsonl"))
+tokenizer_path = os.getenv("TOKENIZER_PATH", "/data/local/hujk/models/Qwen3-8B")
+
+first_line = traj_path.read_text().splitlines()[0]
+record = json.loads(first_line)
+messages = record["trajectory"]
+tools = record.get("tools")
+
+ignore_flag = is_ignore_reasoning_enabled()
+filtered = filter_reasoning_messages(messages, ignore_flag)
+# Sanitize contents to strings for deterministic rendering.
+sanitized = []
+for m in filtered:
+    m = dict(m)
+    if m.get("content") is None:
+        m["content"] = ""
+    elif not isinstance(m.get("content"), str):
+        m["content"] = json.dumps(m["content"])
+    sanitized.append(m)
+
+print(f"IGNORE_REASONING_MESSAGES={ignore_flag}")
+print(f"Messages: original={len(messages)} filtered={len(filtered)}")
+print(
+    "Reasoning messages removed:",
+    len([m for m in messages if "reasoning_content" in m]) - len(
+        [m for m in filtered if "reasoning_content" in m]
+    ),
+)
+
+tok = AutoTokenizer.from_pretrained(tokenizer_path)
+if tok.pad_token is None:
+    tok.pad_token = tok.eos_token
+
+input_ids, instr_mask, data_mask, segment_type, is_normal_token, _custom_mask, rendered = apply_chat_with_tokenize_with_mark(
+    sanitized, tok, tools=tools
+)
+orig_ids, orig_render = apply_chat_with_tokenize_original(sanitized, tok, tools=tools)
+
+print(f"Token count: {len(input_ids)}")
+print(f"Instruction tokens: {sum(instr_mask)}")
+print(f"Data tokens: {sum(data_mask)}")
+print(f"Segment labels present: {sorted(set(segment_type))}")
+print(f"input_ids match original: {input_ids == orig_ids}")
+print("\nRendered preview with markers (first 300 chars):")
+print(rendered[:300])
+cleaned = strip_markers(rendered)
+print("\nRendered preview (markers stripped, first 300 chars):")
+print(cleaned[:300])
+
+# Detailed token/mask dump
+tokens = [tok.decode(t).replace("\n","\\n") for t in input_ids]
+print("\nidx\tinstr\tdata\tseg\tnorm\ttoken")
+for i, (t, im, dm, seg, norm) in enumerate(zip(tokens, instr_mask, data_mask, segment_type, is_normal_token)):
+    print(f"{i}\t{int(im)}\t{int(dm)}\t{seg}\t{int(norm)}\t{t}")
+
+print("\n--- Original apply_chat_template + tokenizer ---")
+orig_tokens = tok.convert_ids_to_tokens(orig_ids)
+for i, t in enumerate(orig_tokens[:50]):
+    human = tok.convert_tokens_to_string([t]) or t
+    print(f"{i}\t{human}")
+PY