diff --git "a/competition/10a_InternLM_h100_analysis.ipynb" "b/competition/10a_InternLM_h100_analysis.ipynb"
--- "a/competition/10a_InternLM_h100_analysis.ipynb"
+++ "b/competition/10a_InternLM_h100_analysis.ipynb"
@@ -1 +1 @@
-{"cells":[{"cell_type":"code","execution_count":1,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{},"inputWidgets":{},"nuid":"0ea8b46b-839b-445b-8043-ccdf4e920ace","showTitle":false,"title":""},"id":"YLH80COBzi_F"},"outputs":[],"source":["%load_ext autoreload\n","%autoreload 2"]},{"cell_type":"code","execution_count":2,"metadata":{"id":"63B5exAuzq4M"},"outputs":[],"source":["from pathlib import Path\n","\n","try:\n","    from google.colab import drive\n","    drive.mount('/content/drive')\n","    workding_dir = \"/content/drive/MyDrive/logical-reasoning/\"\n","except ModuleNotFoundError:\n","    workding_dir = str(Path.cwd().parent)"]},{"cell_type":"code","execution_count":3,"metadata":{"executionInfo":{"elapsed":368,"status":"ok","timestamp":1719461634865,"user":{"displayName":"Donghao Huang","userId":"00463591218503521679"},"user_tz":-480},"id":"zFulf0bg0H-9","outputId":"debdd535-c828-40b9-efc0-8a180e5830dd"},"outputs":[{"name":"stdout","output_type":"stream","text":["workding dir: /Users/inflaton/code/engd/projects/logical-reasoning\n"]}],"source":["import os\n","import sys\n","\n","os.chdir(workding_dir)\n","sys.path.append(workding_dir)\n","print(\"workding dir:\", workding_dir)"]},{"cell_type":"code","execution_count":4,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{},"inputWidgets":{},"nuid":"9f67ec60-2f24-411c-84eb-0dd664b44775","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":589,"status":"ok","timestamp":1719462011879,"user":{"displayName":"Donghao Huang","userId":"00463591218503521679"},"user_tz":-480},"id":"DIUiweYYzi_I","outputId":"e16e9247-9077-4b0c-f8ea-17059f05a1c4"},"outputs":[{"name":"stdout","output_type":"stream","text":["loading env vars from: /Users/inflaton/code/engd/projects/logical-reasoning/.env.example\n"]},{"data":{"text/plain":["True"]},"execution_count":4,"metadata":{},"output_type":"execute_result"}],"source":["from dotenv import find_dotenv, load_dotenv\n","\n","found_dotenv = find_dotenv(\".env\")\n","\n","if len(found_dotenv) == 0:\n","    found_dotenv = find_dotenv(\".env.example\")\n","print(f\"loading env vars from: {found_dotenv}\")\n","load_dotenv(found_dotenv, override=True)"]},{"cell_type":"code","execution_count":5,"metadata":{},"outputs":[],"source":["import re\n","\n","\n","def clean_up(df, model_name):\n","    df[model_name] = df[model_name].apply(\n","        lambda x: re.sub(r\"回答.*是\", \"是\", x)\n","        .replace(\"是男孩\", \"是\")\n","        .replace(\"。\", \"\")\n","        .strip()\n","    )\n","    return df"]},{"cell_type":"code","execution_count":6,"metadata":{"id":"W2QyVreqhOGM","outputId":"68b9590e-1ac6-4c6f-e0c4-e273ec816419"},"outputs":[{"ename":"FileNotFoundError","evalue":"[Errno 2] No such file or directory: 'results/mgtv-results_bf16.csv'","output_type":"error","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)","Cell \u001b[0;32mIn[6], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mpandas\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mpd\u001b[39;00m\n\u001b[0;32m----> 3\u001b[0m df \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mresults/mgtv-results_bf16.csv\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m      4\u001b[0m df \u001b[38;5;241m=\u001b[39m clean_up(df, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124minternlm/internlm2_5-7b-chat-1m\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m      5\u001b[0m df\n","File \u001b[0;32m~/anaconda3/envs/llm-finetuning/lib/python3.11/site-packages/pandas/io/parsers/readers.py:1026\u001b[0m, in \u001b[0;36mread_csv\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[1;32m   1013\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[1;32m   1014\u001b[0m     dialect,\n\u001b[1;32m   1015\u001b[0m     delimiter,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1022\u001b[0m     dtype_backend\u001b[38;5;241m=\u001b[39mdtype_backend,\n\u001b[1;32m   1023\u001b[0m )\n\u001b[1;32m   1024\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[0;32m-> 1026\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m~/anaconda3/envs/llm-finetuning/lib/python3.11/site-packages/pandas/io/parsers/readers.py:620\u001b[0m, in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m    617\u001b[0m _validate_names(kwds\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnames\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[1;32m    619\u001b[0m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[0;32m--> 620\u001b[0m parser \u001b[38;5;241m=\u001b[39m \u001b[43mTextFileReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    622\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[1;32m    623\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m parser\n","File \u001b[0;32m~/anaconda3/envs/llm-finetuning/lib/python3.11/site-packages/pandas/io/parsers/readers.py:1620\u001b[0m, in \u001b[0;36mTextFileReader.__init__\u001b[0;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[1;32m   1617\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m   1619\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles: IOHandles \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1620\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m~/anaconda3/envs/llm-finetuning/lib/python3.11/site-packages/pandas/io/parsers/readers.py:1880\u001b[0m, in \u001b[0;36mTextFileReader._make_engine\u001b[0;34m(self, f, engine)\u001b[0m\n\u001b[1;32m   1878\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[1;32m   1879\u001b[0m         mode \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m-> 1880\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;241m=\u001b[39m \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1881\u001b[0m \u001b[43m    \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1882\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1883\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1884\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcompression\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcompression\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1885\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmemory_map\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmemory_map\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1886\u001b[0m \u001b[43m    \u001b[49m\u001b[43mis_text\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mis_text\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1887\u001b[0m \u001b[43m    \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding_errors\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstrict\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1888\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstorage_options\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1889\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1890\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1891\u001b[0m f \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles\u001b[38;5;241m.\u001b[39mhandle\n","File \u001b[0;32m~/anaconda3/envs/llm-finetuning/lib/python3.11/site-packages/pandas/io/common.py:873\u001b[0m, in \u001b[0;36mget_handle\u001b[0;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[1;32m    868\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[1;32m    869\u001b[0m     \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[1;32m    870\u001b[0m     \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[1;32m    871\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mencoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mmode:\n\u001b[1;32m    872\u001b[0m         \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[0;32m--> 873\u001b[0m         handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m    874\u001b[0m \u001b[43m            \u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    875\u001b[0m \u001b[43m            \u001b[49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    876\u001b[0m \u001b[43m            \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    877\u001b[0m \u001b[43m            \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    878\u001b[0m \u001b[43m            \u001b[49m\u001b[43mnewline\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    879\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    880\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    881\u001b[0m         \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[1;32m    882\u001b[0m         handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(handle, ioargs\u001b[38;5;241m.\u001b[39mmode)\n","\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'results/mgtv-results_bf16.csv'"]}],"source":["import pandas as pd\n","\n","df = pd.read_csv(\"results/mgtv-results_bf16.csv\")\n","df = clean_up(df, \"internlm/internlm2_5-7b-chat-1m\")\n","df"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>text</th>\n","      <th>label</th>\n","      <th>title</th>\n","      <th>puzzle</th>\n","      <th>truth</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-44</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-88</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-132</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-176</th>\n","      <th>internlm/internlm2_5-7b-chat-1m</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>甄加索是自杀吗</td>\n","      <td>不是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>甄加索有身体上的疾病吗</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>画作是甄的</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>甄有心脏病吗</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>车轮是凶手留下的</td>\n","      <td>不是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>...</th>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","    </tr>\n","    <tr>\n","      <th>2995</th>\n","      <td>哭泣者必须在晚上祭奠吗</td>\n","      <td>是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>2996</th>\n","      <td>尸体在湖里吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>2997</th>\n","      <td>哭泣者和死者有特殊关系吗</td>\n","      <td>是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2998</th>\n","      <td>是帽子的主人去世了吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2999</th>\n","      <td>死者受伤了吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不是</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>3000 rows × 10 columns</p>\n","</div>"],"text/plain":["              text label title  \\\n","0          甄加索是自杀吗    不是  海岸之谜   \n","1      甄加索有身体上的疾病吗     是  海岸之谜   \n","2            画作是甄的     是  海岸之谜   \n","3           甄有心脏病吗     是  海岸之谜   \n","4         车轮是凶手留下的    不是  海岸之谜   \n","...            ...   ...   ...   \n","2995   哭泣者必须在晚上祭奠吗     是  甄庄哭声   \n","2996        尸体在湖里吗    不是  甄庄哭声   \n","2997  哭泣者和死者有特殊关系吗     是  甄庄哭声   \n","2998    是帽子的主人去世了吗    不是  甄庄哭声   \n","2999        死者受伤了吗    不是  甄庄哭声   \n","\n","                                                 puzzle  \\\n","0     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","1     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","2     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","3     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","4     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","...                                                 ...   \n","2995  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2996  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2997  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2998  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2999  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","\n","                                                  truth  \\\n","0     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","1     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","2     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","3     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","4     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","...                                                 ...   \n","2995  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2996  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2997  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2998  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2999  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-44  \\\n","0                                               不是   \n","1                                                是   \n","2                                                是   \n","3                                                是   \n","4                                               不是   \n","...                                            ...   \n","2995                                           不重要   \n","2996                                            不是   \n","2997                                             是   \n","2998                                             是   \n","2999                                           不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-88  \\\n","0                                               不是   \n","1                                                是   \n","2                                                是   \n","3                                                是   \n","4                                               不是   \n","...                                            ...   \n","2995                                           不重要   \n","2996                                            不是   \n","2997                                             是   \n","2998                                             是   \n","2999                                           不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-132  \\\n","0                                                不是   \n","1                                                 是   \n","2                                                 是   \n","3                                                 是   \n","4                                                不是   \n","...                                             ...   \n","2995                                            不重要   \n","2996                                             不是   \n","2997                                              是   \n","2998                                              是   \n","2999                                            不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-176  \\\n","0                                                不是   \n","1                                                 是   \n","2                                                 是   \n","3                                                 是   \n","4                                                不是   \n","...                                             ...   \n","2995                                            不重要   \n","2996                                             不是   \n","2997                                              是   \n","2998                                              是   \n","2999                                            不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m  \n","0                                 不是  \n","1                                  是  \n","2                                 不是  \n","3                                  是  \n","4                                 不是  \n","...                              ...  \n","2995                              不是  \n","2996                              不是  \n","2997                               是  \n","2998                               是  \n","2999                              不是  \n","\n","[3000 rows x 10 columns]"]},"execution_count":10,"metadata":{},"output_type":"execute_result"}],"source":["df_h100 = pd.read_csv(\"results/mgtv-results_h100.csv\")\n","df_h100[\"internlm/internlm2_5-7b-chat-1m\"] = df[\"internlm/internlm2_5-7b-chat-1m\"]\n","df = df_h100\n","df"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[{"data":{"text/plain":["['text',\n"," 'label',\n"," 'title',\n"," 'puzzle',\n"," 'truth',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-44',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-88',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-132',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-176',\n"," 'internlm/internlm2_5-7b-chat-1m']"]},"execution_count":11,"metadata":{},"output_type":"execute_result"}],"source":["cols = df.columns.tolist()\n","cols"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[{"data":{"text/plain":["['text',\n"," 'label',\n"," 'title',\n"," 'puzzle',\n"," 'truth',\n"," 'internlm/internlm2_5-7b-chat-1m',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-44',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-88',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-132',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-176']"]},"execution_count":12,"metadata":{},"output_type":"execute_result"}],"source":["# re-order columns\n","\n","cols = cols[:5] + cols[-1:] + cols[5:-1]\n","cols"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>text</th>\n","      <th>label</th>\n","      <th>title</th>\n","      <th>puzzle</th>\n","      <th>truth</th>\n","      <th>internlm/internlm2_5-7b-chat-1m</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-44</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-88</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-132</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-176</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>甄加索是自杀吗</td>\n","      <td>不是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>甄加索有身体上的疾病吗</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>画作是甄的</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>甄有心脏病吗</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>车轮是凶手留下的</td>\n","      <td>不是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>...</th>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","    </tr>\n","    <tr>\n","      <th>2995</th>\n","      <td>哭泣者必须在晚上祭奠吗</td>\n","      <td>是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不是</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","    </tr>\n","    <tr>\n","      <th>2996</th>\n","      <td>尸体在湖里吗</td>\n","      <td>不是</td>\n","      <td>��庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>2997</th>\n","      <td>哭泣者和死者有特殊关系吗</td>\n","      <td>是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2998</th>\n","      <td>是帽子的主人去世了吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2999</th>\n","      <td>死者受伤了吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不是</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>3000 rows × 10 columns</p>\n","</div>"],"text/plain":["              text label title  \\\n","0          甄加索是自杀吗    不是  海岸之谜   \n","1      甄加索有身体上的疾病吗     是  海岸之谜   \n","2            画作是甄的     是  海岸之谜   \n","3           甄有心脏病吗     是  海岸之谜   \n","4         车轮是凶手留下的    不是  海岸之谜   \n","...            ...   ...   ...   \n","2995   哭泣者必须在晚上祭奠吗     是  甄庄哭声   \n","2996        尸体在湖里吗    不是  甄庄哭声   \n","2997  哭泣者和死者有特殊关系吗     是  甄庄哭声   \n","2998    是帽子的主人去世了吗    不是  甄庄哭声   \n","2999        死者受伤了吗    不是  甄庄哭声   \n","\n","                                                 puzzle  \\\n","0     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","1     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","2     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","3     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","4     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","...                                                 ...   \n","2995  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2996  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2997  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2998  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2999  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","\n","                                                  truth  \\\n","0     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","1     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。��他生命的最后几天，他一直在...   \n","2     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","3     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","4     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","...                                                 ...   \n","2995  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2996  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2997  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2998  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2999  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","\n","     internlm/internlm2_5-7b-chat-1m  \\\n","0                                 不是   \n","1                                  是   \n","2                                 不是   \n","3                                  是   \n","4                                 不是   \n","...                              ...   \n","2995                              不是   \n","2996                              不是   \n","2997                               是   \n","2998                               是   \n","2999                              不是   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-44  \\\n","0                                               不是   \n","1                                                是   \n","2                                                是   \n","3                                                是   \n","4                                               不是   \n","...                                            ...   \n","2995                                           不重要   \n","2996                                            不是   \n","2997                                             是   \n","2998                                             是   \n","2999                                           不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-88  \\\n","0                                               不是   \n","1                                                是   \n","2                                                是   \n","3                                                是   \n","4                                               不是   \n","...                                            ...   \n","2995                                           不重要   \n","2996                                            不是   \n","2997                                             是   \n","2998                                             是   \n","2999                                           不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-132  \\\n","0                                                不是   \n","1                                                 是   \n","2                                                 是   \n","3                                                 是   \n","4                                                不是   \n","...                                             ...   \n","2995                                            不重要   \n","2996                                             不是   \n","2997                                              是   \n","2998                                              是   \n","2999                                            不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-176  \n","0                                                不是  \n","1                                                 是  \n","2                                                 是  \n","3                                                 是  \n","4                                                不是  \n","...                                             ...  \n","2995                                            不重要  \n","2996                                             不是  \n","2997                                              是  \n","2998                                              是  \n","2999                                            不重要  \n","\n","[3000 rows x 10 columns]"]},"execution_count":14,"metadata":{},"output_type":"execute_result"}],"source":["df = df[cols]\n","df"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[],"source":["import matplotlib.pyplot as plt\n","from matplotlib import rcParams\n","\n","def plot_value_counts(df, column):\n","    font_family = rcParams[\"font.family\"]\n","    # Set the font to SimHei to support Chinese characters\n","    rcParams[\"font.family\"] = \"STHeiti\"\n","    rcParams[\"axes.unicode_minus\"] = False  # This is to support the minus sign in Chinese.\n","\n","    plt.figure(figsize=(12, 6))\n","    df[column].value_counts().plot(kind=\"bar\")\n","    # add values on top of bars\n","    for i, v in enumerate(df[column].value_counts()):\n","        plt.text(i, v + 0.1, str(v), ha=\"center\")\n","    plt.show()\n","    \n","    rcParams[\"font.family\"] = font_family\n"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[{"data":{"text/plain":["['text',\n"," 'label',\n"," 'title',\n"," 'puzzle',\n"," 'truth',\n"," 'internlm/internlm2_5-7b-chat-1m',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-44',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-88',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-132',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-176']"]},"execution_count":16,"metadata":{},"output_type":"execute_result"}],"source":["df.columns.to_list()"]},{"cell_type":"code","execution_count":8,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["/Users/inflaton/anaconda3/envs/llm-finetuning/lib/python3.11/site-packages/matplotlib/mpl-data/matplotlibrc\n"]}],"source":["import matplotlib\n","print(matplotlib.matplotlib_fname())"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[{"name":"stderr","output_type":"stream","text":["findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 19981 (\\N{CJK UNIFIED IDEOGRAPH-4E0D}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 26159 (\\N{CJK UNIFIED IDEOGRAPH-662F}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 37325 (\\N{CJK UNIFIED IDEOGRAPH-91CD}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 35201 (\\N{CJK UNIFIED IDEOGRAPH-8981}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n"]},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m **********\n","internlm/internlm2_5-7b-chat-1m\n","不是     1670\n","是      1284\n","不重要      46\n","Name: count, dtype: int64\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stderr","output_type":"stream","text":["findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 19981 (\\N{CJK UNIFIED IDEOGRAPH-4E0D}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 26159 (\\N{CJK UNIFIED IDEOGRAPH-662F}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 37325 (\\N{CJK UNIFIED IDEOGRAPH-91CD}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 35201 (\\N{CJK UNIFIED IDEOGRAPH-8981}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 22238 (\\N{CJK UNIFIED IDEOGRAPH-56DE}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 31572 (\\N{CJK UNIFIED IDEOGRAPH-7B54}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 27491 (\\N{CJK UNIFIED IDEOGRAPH-6B63}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 30830 (\\N{CJK UNIFIED IDEOGRAPH-786E}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 38382 (\\N{CJK UNIFIED IDEOGRAPH-95EE}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 27861 (\\N{CJK UNIFIED IDEOGRAPH-6CD5}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 38169 (\\N{CJK UNIFIED IDEOGRAPH-9519}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 35823 (\\N{CJK UNIFIED IDEOGRAPH-8BEF}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n"]},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-44 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-44\n","不是      1329\n","是       1213\n","不重要      377\n","回答正确      42\n","问法错误      39\n","Name: count, dtype: int64\n"]},{"name":"stderr","output_type":"stream","text":["findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stderr","output_type":"stream","text":["findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 19981 (\\N{CJK UNIFIED IDEOGRAPH-4E0D}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 26159 (\\N{CJK UNIFIED IDEOGRAPH-662F}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 37325 (\\N{CJK UNIFIED IDEOGRAPH-91CD}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 35201 (\\N{CJK UNIFIED IDEOGRAPH-8981}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 38382 (\\N{CJK UNIFIED IDEOGRAPH-95EE}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 27861 (\\N{CJK UNIFIED IDEOGRAPH-6CD5}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 38169 (\\N{CJK UNIFIED IDEOGRAPH-9519}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 35823 (\\N{CJK UNIFIED IDEOGRAPH-8BEF}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 22238 (\\N{CJK UNIFIED IDEOGRAPH-56DE}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 31572 (\\N{CJK UNIFIED IDEOGRAPH-7B54}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 27491 (\\N{CJK UNIFIED IDEOGRAPH-6B63}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 30830 (\\N{CJK UNIFIED IDEOGRAPH-786E}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n"]},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-88 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-88\n","不是      1288\n","是       1154\n","不重要      470\n","问法错误      53\n","回答正确      35\n","Name: count, dtype: int64\n"]},{"name":"stderr","output_type":"stream","text":["findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stderr","output_type":"stream","text":["findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 19981 (\\N{CJK UNIFIED IDEOGRAPH-4E0D}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 26159 (\\N{CJK UNIFIED IDEOGRAPH-662F}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 37325 (\\N{CJK UNIFIED IDEOGRAPH-91CD}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 35201 (\\N{CJK UNIFIED IDEOGRAPH-8981}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 38382 (\\N{CJK UNIFIED IDEOGRAPH-95EE}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 27861 (\\N{CJK UNIFIED IDEOGRAPH-6CD5}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 38169 (\\N{CJK UNIFIED IDEOGRAPH-9519}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 35823 (\\N{CJK UNIFIED IDEOGRAPH-8BEF}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 22238 (\\N{CJK UNIFIED IDEOGRAPH-56DE}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 31572 (\\N{CJK UNIFIED IDEOGRAPH-7B54}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 27491 (\\N{CJK UNIFIED IDEOGRAPH-6B63}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 30830 (\\N{CJK UNIFIED IDEOGRAPH-786E}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n"]},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-132 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-132\n","不是      1314\n","是       1211\n","不重要      398\n","问法错误      40\n","回答正确      37\n","Name: count, dtype: int64\n"]},{"name":"stderr","output_type":"stream","text":["findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stderr","output_type":"stream","text":["findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 19981 (\\N{CJK UNIFIED IDEOGRAPH-4E0D}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 26159 (\\N{CJK UNIFIED IDEOGRAPH-662F}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 37325 (\\N{CJK UNIFIED IDEOGRAPH-91CD}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 35201 (\\N{CJK UNIFIED IDEOGRAPH-8981}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 38382 (\\N{CJK UNIFIED IDEOGRAPH-95EE}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 27861 (\\N{CJK UNIFIED IDEOGRAPH-6CD5}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 38169 (\\N{CJK UNIFIED IDEOGRAPH-9519}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 35823 (\\N{CJK UNIFIED IDEOGRAPH-8BEF}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 22238 (\\N{CJK UNIFIED IDEOGRAPH-56DE}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 31572 (\\N{CJK UNIFIED IDEOGRAPH-7B54}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 27491 (\\N{CJK UNIFIED IDEOGRAPH-6B63}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 30830 (\\N{CJK UNIFIED IDEOGRAPH-786E}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 27515 (\\N{CJK UNIFIED IDEOGRAPH-6B7B}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 20129 (\\N{CJK UNIFIED IDEOGRAPH-4EA1}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 24456 (\\N{CJK UNIFIED IDEOGRAPH-5F88}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 20037 (\\N{CJK UNIFIED IDEOGRAPH-4E45}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/IPython/core/pylabtools.py:170: UserWarning: Glyph 20102 (\\N{CJK UNIFIED IDEOGRAPH-4E86}) missing from font(s) DejaVu Sans.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n"]},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-176 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-176\n","不是       1243\n","是        1155\n","不重要       497\n","问法错误       69\n","回答正确       35\n","死亡很久了       1\n","Name: count, dtype: int64\n"]},{"name":"stderr","output_type":"stream","text":["findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n","findfont: Font family 'STHeiti' not found.\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["for col in df.columns[5:]:\n","    print(\"*\" * 10, col, \"*\" * 10)\n","    print(df[col].value_counts())\n","    plot_value_counts(df, col)"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[],"source":["import pandas as pd\n","import numpy as np\n","from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\n","\n","\n","def calc_metrics_for_col(df, col):\n","    y_true = df[\"label\"]\n","    y_pred = df[col]\n","\n","    accuracy = accuracy_score(y_true, y_pred)\n","    precision = precision_score(y_true, y_pred, average=\"weighted\", labels=np.unique(y_pred))\n","    recall = recall_score(y_true, y_pred, average=\"weighted\", labels=np.unique(y_pred))\n","    f1 = f1_score(y_true, y_pred, average=\"weighted\", labels=np.unique(y_pred))\n","\n","    return accuracy, float(precision), float(recall), float(f1)"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[{"name":"stderr","output_type":"stream","text":["/tmp/ipykernel_26059/961288552.py:9: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n","  perf_df = pd.concat([perf_df, pd.DataFrame([new_model_metrics])], ignore_index=True)\n","/home/inflaton/miniconda3/envs/llama-factory/lib/python3.11/site-packages/sklearn/metrics/_classification.py:1517: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.\n","  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n"]},{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>epoch</th>\n","      <th>model</th>\n","      <th>accuracy</th>\n","      <th>precision</th>\n","      <th>recall</th>\n","      <th>f1</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>0</td>\n","      <td>internlm/internlm2_5-7b-chat-1m</td>\n","      <td>0.759667</td>\n","      <td>0.741854</td>\n","      <td>0.781014</td>\n","      <td>0.758887</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>1</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-44</td>\n","      <td>0.761667</td>\n","      <td>0.810873</td>\n","      <td>0.761667</td>\n","      <td>0.780018</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-88</td>\n","      <td>0.741333</td>\n","      <td>0.816182</td>\n","      <td>0.741333</td>\n","      <td>0.769524</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>3</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-132</td>\n","      <td>0.755000</td>\n","      <td>0.809829</td>\n","      <td>0.755000</td>\n","      <td>0.775657</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>4</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-176</td>\n","      <td>0.719000</td>\n","      <td>0.803611</td>\n","      <td>0.719000</td>\n","      <td>0.750460</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["  epoch                                           model  accuracy  precision  \\\n","0     0                 internlm/internlm2_5-7b-chat-1m  0.759667   0.741854   \n","1     1   internlm/internlm2_5-7b-chat-1m_checkpoint-44  0.761667   0.810873   \n","2     2   internlm/internlm2_5-7b-chat-1m_checkpoint-88  0.741333   0.816182   \n","3     3  internlm/internlm2_5-7b-chat-1m_checkpoint-132  0.755000   0.809829   \n","4     4  internlm/internlm2_5-7b-chat-1m_checkpoint-176  0.719000   0.803611   \n","\n","     recall        f1  \n","0  0.781014  0.758887  \n","1  0.761667  0.780018  \n","2  0.741333  0.769524  \n","3  0.755000  0.775657  \n","4  0.719000  0.750460  "]},"execution_count":19,"metadata":{},"output_type":"execute_result"}],"source":["import pandas as pd\n","\n","perf_df = pd.DataFrame(columns=[\"epoch\", \"model\", \"accuracy\", \"precision\", \"recall\", \"f1\"])\n","for i, col in enumerate(df.columns[5:]):\n","    accuracy, precision, recall, f1 = calc_metrics_for_col(df, col)\n","    new_model_metrics = {\"epoch\": i, \"model\": col, \"accuracy\": accuracy, \"precision\": precision, \"recall\": recall, \"f1\": f1}\n","\n","    # Convert the dictionary to a DataFrame and concatenate it with the existing DataFrame\n","    perf_df = pd.concat([perf_df, pd.DataFrame([new_model_metrics])], ignore_index=True)\n","\n","perf_df"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[{"data":{"image/png":"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","text/plain":["<Figure size 1200x500 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["# plot metrics for each model\n","import matplotlib.pyplot as plt\n","\n","fig, ax = plt.subplots(1, 1, figsize=(12, 5))\n","\n","perf_df.plot(x=\"epoch\", y=[\"accuracy\", \"precision\", \"recall\", \"f1\"], kind=\"bar\", ax=ax)\n","\n","# add values on top of bars\n","for p in ax.patches:\n","    ax.annotate(\n","        f\"{p.get_height():.2f}\",\n","        (p.get_x() + p.get_width() / 2, p.get_height()),\n","        ha=\"center\",\n","        va=\"bottom\",\n","        fontsize=10,\n","    )\n","\n","# add title and labels\n","# ax.set_title(\"Metrics for different settings\")\n","# ax.set_ylabel(\"Value\")\n","ax.set_xlabel(\"Epoch (0: base model, 1-4: fine-tuned models)\")\n","# rotate x labels\n","plt.xticks(rotation=0)\n","\n","# set legend at the right to avoid overlapping with bars\n","plt.legend(loc=\"center left\", bbox_to_anchor=(1.0, 0.5))\n","# plt.tight_layout()\n","\n","plt.show()"]}],"metadata":{"accelerator":"GPU","application/vnd.databricks.v1+notebook":{"dashboards":[],"environmentMetadata":null,"language":"python","notebookMetadata":{"pythonIndentUnit":4},"notebookName":"07_MAC_+_Qwen2-7B-Instructi_Unsloth_train","widgets":{}},"colab":{"gpuType":"T4","provenance":[]},"kernelspec":{"display_name":"Python 3","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.11.9"}},"nbformat":4,"nbformat_minor":0}
+{"cells":[{"cell_type":"code","execution_count":1,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{},"inputWidgets":{},"nuid":"0ea8b46b-839b-445b-8043-ccdf4e920ace","showTitle":false,"title":""},"id":"YLH80COBzi_F"},"outputs":[],"source":["%load_ext autoreload\n","%autoreload 2"]},{"cell_type":"code","execution_count":2,"metadata":{"id":"63B5exAuzq4M"},"outputs":[],"source":["from pathlib import Path\n","\n","try:\n","    from google.colab import drive\n","    drive.mount('/content/drive')\n","    workding_dir = \"/content/drive/MyDrive/logical-reasoning/\"\n","except ModuleNotFoundError:\n","    workding_dir = str(Path.cwd().parent)"]},{"cell_type":"code","execution_count":3,"metadata":{"executionInfo":{"elapsed":368,"status":"ok","timestamp":1719461634865,"user":{"displayName":"Donghao Huang","userId":"00463591218503521679"},"user_tz":-480},"id":"zFulf0bg0H-9","outputId":"debdd535-c828-40b9-efc0-8a180e5830dd"},"outputs":[{"name":"stdout","output_type":"stream","text":["workding dir: /Users/inflaton/code/engd/projects/logical-reasoning\n"]}],"source":["import os\n","import sys\n","\n","os.chdir(workding_dir)\n","sys.path.append(workding_dir)\n","print(\"workding dir:\", workding_dir)"]},{"cell_type":"code","execution_count":4,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{},"inputWidgets":{},"nuid":"9f67ec60-2f24-411c-84eb-0dd664b44775","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":589,"status":"ok","timestamp":1719462011879,"user":{"displayName":"Donghao Huang","userId":"00463591218503521679"},"user_tz":-480},"id":"DIUiweYYzi_I","outputId":"e16e9247-9077-4b0c-f8ea-17059f05a1c4"},"outputs":[{"name":"stdout","output_type":"stream","text":["loading env vars from: /Users/inflaton/code/engd/projects/logical-reasoning/.env.example\n"]},{"data":{"text/plain":["True"]},"execution_count":4,"metadata":{},"output_type":"execute_result"}],"source":["from dotenv import find_dotenv, load_dotenv\n","\n","found_dotenv = find_dotenv(\".env\")\n","\n","if len(found_dotenv) == 0:\n","    found_dotenv = find_dotenv(\".env.example\")\n","print(f\"loading env vars from: {found_dotenv}\")\n","load_dotenv(found_dotenv, override=True)"]},{"cell_type":"code","execution_count":5,"metadata":{"id":"W2QyVreqhOGM","outputId":"68b9590e-1ac6-4c6f-e0c4-e273ec816419"},"outputs":[{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>text</th>\n","      <th>label</th>\n","      <th>title</th>\n","      <th>puzzle</th>\n","      <th>truth</th>\n","      <th>internlm/internlm2_5-7b-chat-1m</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-562</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-1124</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-1686</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-2248</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>甄加索是自杀吗</td>\n","      <td>不是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>甄加索有身体上的疾病吗</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>画作是甄的</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>是</td>\n","      <td>不重要</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>甄有心脏病吗</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻���灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>车轮是凶手留下的</td>\n","      <td>不是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>不重要</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>...</th>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","    </tr>\n","    <tr>\n","      <th>2995</th>\n","      <td>哭泣者必须在晚上祭奠吗</td>\n","      <td>是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不是</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","    </tr>\n","    <tr>\n","      <th>2996</th>\n","      <td>尸体在湖里吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不是</td>\n","      <td>不重要</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>2997</th>\n","      <td>哭泣者和死者有特殊关系吗</td>\n","      <td>是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2998</th>\n","      <td>是帽子的主人去世了吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2999</th>\n","      <td>死者受伤了吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不是</td>\n","      <td>不重要</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>3000 rows × 10 columns</p>\n","</div>"],"text/plain":["              text label title  \\\n","0          甄加索是自杀吗    不是  海岸之谜   \n","1      甄加索有身体上的疾病吗     是  海岸之谜   \n","2            画作是甄的     是  海岸之谜   \n","3           甄有心脏病吗     是  海岸之谜   \n","4         车轮是凶手留下的    不是  海岸之谜   \n","...            ...   ...   ...   \n","2995   哭泣者必须在晚上祭奠吗     是  甄庄哭声   \n","2996        尸体在湖里吗    不是  甄庄哭声   \n","2997  哭泣者和死者有特殊关系吗     是  甄庄哭声   \n","2998    是帽子的主人去世了吗    不是  甄庄哭声   \n","2999        死者受伤了吗    不是  甄庄哭声   \n","\n","                                                 puzzle  \\\n","0     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场��有发现任...   \n","1     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","2     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","3     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","4     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","...                                                 ...   \n","2995  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2996  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2997  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2998  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2999  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","\n","                                                  truth  \\\n","0     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","1     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","2     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","3     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","4     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","...                                                 ...   \n","2995  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2996  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2997  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2998  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2999  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","\n","     internlm/internlm2_5-7b-chat-1m  \\\n","0                                 不是   \n","1                                  是   \n","2                                 不是   \n","3                                  是   \n","4                                 不是   \n","...                              ...   \n","2995                              不是   \n","2996                              不是   \n","2997                               是   \n","2998                               是   \n","2999                              不是   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-562  \\\n","0                                                不是   \n","1                                                 是   \n","2                                                 是   \n","3                                                 是   \n","4                                               不重要   \n","...                                             ...   \n","2995                                            不重要   \n","2996                                            不重要   \n","2997                                              是   \n","2998                                              是   \n","2999                                            不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-1124  \\\n","0                                                 不是   \n","1                                                  是   \n","2                                                不重要   \n","3                                                  是   \n","4                                                 不是   \n","...                                              ...   \n","2995                                             不重要   \n","2996                                              不是   \n","2997                                               是   \n","2998                                               是   \n","2999                                              不是   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-1686  \\\n","0                                                 不是   \n","1                                                  是   \n","2                                                  是   \n","3                                                  是   \n","4                                                 不是   \n","...                                              ...   \n","2995                                             不重要   \n","2996                                              不是   \n","2997                                               是   \n","2998                                               是   \n","2999                                              不是   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-2248  \n","0                                                 不是  \n","1                                                  是  \n","2                                                  是  \n","3                                                  是  \n","4                                                 不是  \n","...                                              ...  \n","2995                                             不重要  \n","2996                                              不是  \n","2997                                               是  \n","2998                                               是  \n","2999                                              不是  \n","\n","[3000 rows x 10 columns]"]},"execution_count":5,"metadata":{},"output_type":"execute_result"}],"source":["import pandas as pd\n","\n","df = pd.read_csv(\"results/mgtv-results_bf16.csv\")\n","df"]},{"cell_type":"code","execution_count":6,"metadata":{},"outputs":[{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>text</th>\n","      <th>label</th>\n","      <th>title</th>\n","      <th>puzzle</th>\n","      <th>truth</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-44</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-88</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-132</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-176</th>\n","      <th>internlm/internlm2_5-7b-chat-1m</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>甄加索是自杀吗</td>\n","      <td>不是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>甄加索有身体上的疾病吗</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>画作是甄的</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>甄有心脏病吗</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>车轮是凶手留下的</td>\n","      <td>不是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>...</th>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","    </tr>\n","    <tr>\n","      <th>2995</th>\n","      <td>哭泣者必须在晚上祭奠吗</td>\n","      <td>是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>2996</th>\n","      <td>尸体在湖里吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>2997</th>\n","      <td>哭泣者和死者有特殊关系吗</td>\n","      <td>是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2998</th>\n","      <td>是帽子的主人去世了吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2999</th>\n","      <td>死者受伤了吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不是</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>3000 rows × 10 columns</p>\n","</div>"],"text/plain":["              text label title  \\\n","0          甄加索是自杀吗    不是  海岸之谜   \n","1      甄加索有身体上的疾病吗     是  海岸之谜   \n","2            画作是甄的     是  海岸之谜   \n","3           甄有心脏病吗     是  海岸之谜   \n","4         车轮是凶手留下的    不是  海岸之谜   \n","...            ...   ...   ...   \n","2995   哭泣者必须在晚上祭奠吗     是  甄庄哭声   \n","2996        尸体在湖里吗    不是  甄庄哭声   \n","2997  哭泣者和死者有特殊关系吗     是  甄庄哭声   \n","2998    是帽子的主人去世了吗    不是  甄庄哭声   \n","2999        死者受伤了吗    不是  甄庄哭声   \n","\n","                                                 puzzle  \\\n","0     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","1     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场���有发现任...   \n","2     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","3     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","4     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","...                                                 ...   \n","2995  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2996  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2997  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2998  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2999  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","\n","                                                  truth  \\\n","0     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","1     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","2     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","3     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","4     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","...                                                 ...   \n","2995  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2996  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2997  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2998  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2999  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-44  \\\n","0                                               不是   \n","1                                                是   \n","2                                                是   \n","3                                                是   \n","4                                               不是   \n","...                                            ...   \n","2995                                           不重要   \n","2996                                            不是   \n","2997                                             是   \n","2998                                             是   \n","2999                                           不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-88  \\\n","0                                               不是   \n","1                                                是   \n","2                                                是   \n","3                                                是   \n","4                                               不是   \n","...                                            ...   \n","2995                                           不重要   \n","2996                                            不是   \n","2997                                             是   \n","2998                                             是   \n","2999                                           不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-132  \\\n","0                                                不是   \n","1                                                 是   \n","2                                                 是   \n","3                                                 是   \n","4                                                不是   \n","...                                             ...   \n","2995                                            不重要   \n","2996                                             不是   \n","2997                                              是   \n","2998                                              是   \n","2999                                            不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-176  \\\n","0                                                不是   \n","1                                                 是   \n","2                                                 是   \n","3                                                 是   \n","4                                                不是   \n","...                                             ...   \n","2995                                            不重要   \n","2996                                             不是   \n","2997                                              是   \n","2998                                              是   \n","2999                                            不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m  \n","0                                 不是  \n","1                                  是  \n","2                                 不是  \n","3                                  是  \n","4                                 不是  \n","...                              ...  \n","2995                              不是  \n","2996                              不是  \n","2997                               是  \n","2998                               是  \n","2999                              不是  \n","\n","[3000 rows x 10 columns]"]},"execution_count":6,"metadata":{},"output_type":"execute_result"}],"source":["df_h100 = pd.read_csv(\"results/mgtv-results_h100.csv\")\n","df_h100[\"internlm/internlm2_5-7b-chat-1m\"] = df[\"internlm/internlm2_5-7b-chat-1m\"]\n","df = df_h100\n","df"]},{"cell_type":"code","execution_count":7,"metadata":{},"outputs":[{"data":{"text/plain":["['text',\n"," 'label',\n"," 'title',\n"," 'puzzle',\n"," 'truth',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-44',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-88',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-132',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-176',\n"," 'internlm/internlm2_5-7b-chat-1m']"]},"execution_count":7,"metadata":{},"output_type":"execute_result"}],"source":["cols = df.columns.tolist()\n","cols"]},{"cell_type":"code","execution_count":8,"metadata":{},"outputs":[{"data":{"text/plain":["['text',\n"," 'label',\n"," 'title',\n"," 'puzzle',\n"," 'truth',\n"," 'internlm/internlm2_5-7b-chat-1m',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-44',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-88',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-132',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-176']"]},"execution_count":8,"metadata":{},"output_type":"execute_result"}],"source":["# re-order columns\n","\n","cols = cols[:5] + cols[-1:] + cols[5:-1]\n","cols"]},{"cell_type":"code","execution_count":9,"metadata":{},"outputs":[{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>text</th>\n","      <th>label</th>\n","      <th>title</th>\n","      <th>puzzle</th>\n","      <th>truth</th>\n","      <th>internlm/internlm2_5-7b-chat-1m</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-44</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-88</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-132</th>\n","      <th>internlm/internlm2_5-7b-chat-1m_checkpoint-176</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>甄加索是自杀吗</td>\n","      <td>不是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>甄加索有身体上的疾病吗</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>画作是甄的</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远��城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>甄有心脏病吗</td>\n","      <td>是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>车轮是凶手留下的</td>\n","      <td>不是</td>\n","      <td>海岸之谜</td>\n","      <td>在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...</td>\n","      <td>甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>...</th>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","    </tr>\n","    <tr>\n","      <th>2995</th>\n","      <td>哭泣者必须在晚上祭奠吗</td>\n","      <td>是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不是</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","    </tr>\n","    <tr>\n","      <th>2996</th>\n","      <td>尸体在湖里吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>2997</th>\n","      <td>哭泣者和死者有特殊关系吗</td>\n","      <td>是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2998</th>\n","      <td>是帽子的主人去世了吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","      <td>是</td>\n","    </tr>\n","    <tr>\n","      <th>2999</th>\n","      <td>死者受伤了吗</td>\n","      <td>不是</td>\n","      <td>甄庄哭声</td>\n","      <td>在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...</td>\n","      <td>原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...</td>\n","      <td>不是</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","      <td>不重要</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>3000 rows × 10 columns</p>\n","</div>"],"text/plain":["              text label title  \\\n","0          甄加索是自杀吗    不是  海岸之谜   \n","1      甄加索有身体上的疾病吗     是  海岸之谜   \n","2            画作是甄的     是  海岸之谜   \n","3           甄有心脏病吗     是  海岸之谜   \n","4         车轮是凶手留下的    不是  海岸之谜   \n","...            ...   ...   ...   \n","2995   哭泣者必须在晚上祭奠吗     是  甄庄哭声   \n","2996        尸体在湖里吗    不是  甄庄哭声   \n","2997  哭泣者和死者有特殊关系吗     是  甄庄哭声   \n","2998    是帽子的主人去世了吗    不是  甄庄哭声   \n","2999        死者受伤了吗    不是  甄庄哭声   \n","\n","                                                 puzzle  \\\n","0     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","1     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","2     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","3     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","4     在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任...   \n","...                                                 ...   \n","2995  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2996  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2997  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2998  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","2999  在一个安静的夜晚，小村庄的湖边突然传来了阵阵哭泣声。第二天早晨，村长甄锐发现湖边的石头上放着...   \n","\n","                                                  truth  \\\n","0     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","1     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","2     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","3     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","4     甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在...   \n","...                                                 ...   \n","2995  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2996  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2997  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2998  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","2999  原来，这顶破旧的帽子属于一个小男孩，他小时候与爷爷在湖边生活。爷爷教他钓鱼、游泳，还告诉他湖...   \n","\n","     internlm/internlm2_5-7b-chat-1m  \\\n","0                                 不是   \n","1                                  是   \n","2                                 不是   \n","3                                  是   \n","4                                 不是   \n","...                              ...   \n","2995                              不是   \n","2996                              不是   \n","2997                               是   \n","2998                               是   \n","2999                              不是   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-44  \\\n","0                                               不是   \n","1                                                是   \n","2                                                是   \n","3                                                是   \n","4                                               不是   \n","...                                            ...   \n","2995                                           不重要   \n","2996                                            不是   \n","2997                                             是   \n","2998                                             是   \n","2999                                           不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-88  \\\n","0                                               不是   \n","1                                                是   \n","2                                                是   \n","3                                                是   \n","4                                               不是   \n","...                                            ...   \n","2995                                           不重要   \n","2996                                            不是   \n","2997                                             是   \n","2998                                             是   \n","2999                                           不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-132  \\\n","0                                                不是   \n","1                                                 是   \n","2                                                 是   \n","3                                                 是   \n","4                                                不是   \n","...                                             ...   \n","2995                                            不重要   \n","2996                                             不是   \n","2997                                              是   \n","2998                                              是   \n","2999                                            不重要   \n","\n","     internlm/internlm2_5-7b-chat-1m_checkpoint-176  \n","0                                                不是  \n","1                                                 是  \n","2                                                 是  \n","3                                                 是  \n","4                                                不是  \n","...                                             ...  \n","2995                                            不重要  \n","2996                                             不是  \n","2997                                              是  \n","2998                                              是  \n","2999                                            不重要  \n","\n","[3000 rows x 10 columns]"]},"execution_count":9,"metadata":{},"output_type":"execute_result"}],"source":["df = df[cols]\n","df"]},{"cell_type":"code","execution_count":10,"metadata":{},"outputs":[],"source":["import matplotlib.pyplot as plt\n","from matplotlib import rcParams\n","\n","def plot_value_counts(df, column):\n","    font_family = rcParams[\"font.family\"]\n","    # Set the font to SimHei to support Chinese characters\n","    rcParams[\"font.family\"] = \"STHeiti\"\n","    rcParams[\"axes.unicode_minus\"] = False  # This is to support the minus sign in Chinese.\n","\n","    plt.figure(figsize=(12, 6))\n","    df[column].value_counts().plot(kind=\"bar\")\n","    # add values on top of bars\n","    for i, v in enumerate(df[column].value_counts()):\n","        plt.text(i, v + 0.1, str(v), ha=\"center\")\n","    plt.show()\n","    \n","    rcParams[\"font.family\"] = font_family\n"]},{"cell_type":"code","execution_count":11,"metadata":{},"outputs":[{"data":{"text/plain":["['text',\n"," 'label',\n"," 'title',\n"," 'puzzle',\n"," 'truth',\n"," 'internlm/internlm2_5-7b-chat-1m',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-44',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-88',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-132',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-176']"]},"execution_count":11,"metadata":{},"output_type":"execute_result"}],"source":["df.columns.to_list()"]},{"cell_type":"code","execution_count":12,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m **********\n","internlm/internlm2_5-7b-chat-1m\n","不是      1670\n","是       1283\n","不重要       43\n","不重要。       3\n","是男孩。       1\n","Name: count, dtype: int64\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-44 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-44\n","不是      1329\n","是       1213\n","不重要      377\n","回答正确      42\n","问法错误      39\n","Name: count, dtype: int64\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-88 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-88\n","不是      1288\n","是       1154\n","不重要      470\n","问法错误      53\n","回答正确      35\n","Name: count, dtype: int64\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-132 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-132\n","不是      1314\n","是       1211\n","不重要      398\n","问法错误      40\n","回答正确      37\n","Name: count, dtype: int64\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-176 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-176\n","不是       1243\n","是        1155\n","不重要       497\n","问法错误       69\n","回答正确       35\n","死亡很久了       1\n","Name: count, dtype: int64\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["for col in df.columns[5:]:\n","    print(\"*\" * 10, col, \"*\" * 10)\n","    print(df[col].value_counts())\n","    plot_value_counts(df, col)"]},{"cell_type":"code","execution_count":13,"metadata":{},"outputs":[],"source":["import re\n","\n","\n","def clean_up(df, model_name):\n","    df[model_name] = df[model_name].apply(\n","        lambda x: re.sub(r\"回答.*是\", \"是\", x)\n","        .replace(\"死亡很久了\", \"是\")\n","        .replace(\"是男孩\", \"是\")\n","        .replace(\"。\", \"\")\n","        .strip()\n","    )\n","    return df"]},{"cell_type":"code","execution_count":14,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m **********\n","internlm/internlm2_5-7b-chat-1m\n","不是     1670\n","是      1284\n","不重要      46\n","Name: count, dtype: int64\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-44 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-44\n","不是      1329\n","是       1213\n","不重要      377\n","回答正确      42\n","问法错误      39\n","Name: count, dtype: int64\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-88 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-88\n","不是      1288\n","是       1154\n","不重要      470\n","问法错误      53\n","回答正确      35\n","Name: count, dtype: int64\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-132 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-132\n","不是      1314\n","是       1211\n","不重要      398\n","问法错误      40\n","回答正确      37\n","Name: count, dtype: int64\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["********** internlm/internlm2_5-7b-chat-1m_checkpoint-176 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-176\n","不是      1243\n","是       1156\n","不重要      497\n","问法错误      69\n","回答正确      35\n","Name: count, dtype: int64\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["for col in df.columns[5:]:\n","    df = clean_up(df, col)\n","    print(\"*\" * 10, col, \"*\" * 10)\n","    print(df[col].value_counts())\n","    plot_value_counts(df, col)"]},{"cell_type":"code","execution_count":15,"metadata":{},"outputs":[],"source":["import pandas as pd\n","import numpy as np\n","from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\n","\n","\n","def calc_metrics_for_col(df, col):\n","    y_true = df[\"label\"]\n","    y_pred = df[col]\n","\n","    accuracy = accuracy_score(y_true, y_pred)\n","    precision = precision_score(y_true, y_pred, average=\"weighted\", labels=np.unique(y_pred))\n","    recall = recall_score(y_true, y_pred, average=\"weighted\", labels=np.unique(y_pred))\n","    f1 = f1_score(y_true, y_pred, average=\"weighted\", labels=np.unique(y_pred))\n","\n","    return accuracy, float(precision), float(recall), float(f1)"]},{"cell_type":"code","execution_count":16,"metadata":{},"outputs":[{"name":"stderr","output_type":"stream","text":["/var/folders/7x/56svhln929zdh2xhr3mwqg4r0000gn/T/ipykernel_89453/961288552.py:9: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n","  perf_df = pd.concat([perf_df, pd.DataFrame([new_model_metrics])], ignore_index=True)\n"]},{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>epoch</th>\n","      <th>model</th>\n","      <th>accuracy</th>\n","      <th>precision</th>\n","      <th>recall</th>\n","      <th>f1</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>0</td>\n","      <td>internlm/internlm2_5-7b-chat-1m</td>\n","      <td>0.759667</td>\n","      <td>0.741854</td>\n","      <td>0.781014</td>\n","      <td>0.758887</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>1</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-44</td>\n","      <td>0.761667</td>\n","      <td>0.810873</td>\n","      <td>0.761667</td>\n","      <td>0.780018</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-88</td>\n","      <td>0.741333</td>\n","      <td>0.816182</td>\n","      <td>0.741333</td>\n","      <td>0.769524</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>3</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-132</td>\n","      <td>0.755000</td>\n","      <td>0.809829</td>\n","      <td>0.755000</td>\n","      <td>0.775657</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>4</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-176</td>\n","      <td>0.719000</td>\n","      <td>0.803307</td>\n","      <td>0.719000</td>\n","      <td>0.750319</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["  epoch                                           model  accuracy  precision  \\\n","0     0                 internlm/internlm2_5-7b-chat-1m  0.759667   0.741854   \n","1     1   internlm/internlm2_5-7b-chat-1m_checkpoint-44  0.761667   0.810873   \n","2     2   internlm/internlm2_5-7b-chat-1m_checkpoint-88  0.741333   0.816182   \n","3     3  internlm/internlm2_5-7b-chat-1m_checkpoint-132  0.755000   0.809829   \n","4     4  internlm/internlm2_5-7b-chat-1m_checkpoint-176  0.719000   0.803307   \n","\n","     recall        f1  \n","0  0.781014  0.758887  \n","1  0.761667  0.780018  \n","2  0.741333  0.769524  \n","3  0.755000  0.775657  \n","4  0.719000  0.750319  "]},"execution_count":16,"metadata":{},"output_type":"execute_result"}],"source":["import pandas as pd\n","\n","perf_df = pd.DataFrame(columns=[\"epoch\", \"model\", \"accuracy\", \"precision\", \"recall\", \"f1\"])\n","for i, col in enumerate(df.columns[5:]):\n","    accuracy, precision, recall, f1 = calc_metrics_for_col(df, col)\n","    new_model_metrics = {\"epoch\": i, \"model\": col, \"accuracy\": accuracy, \"precision\": precision, \"recall\": recall, \"f1\": f1}\n","\n","    # Convert the dictionary to a DataFrame and concatenate it with the existing DataFrame\n","    perf_df = pd.concat([perf_df, pd.DataFrame([new_model_metrics])], ignore_index=True)\n","\n","perf_df"]},{"cell_type":"code","execution_count":17,"metadata":{},"outputs":[{"data":{"image/png":"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","text/plain":["<Figure size 1200x500 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["# plot metrics for each model\n","import matplotlib.pyplot as plt\n","\n","fig, ax = plt.subplots(1, 1, figsize=(12, 5))\n","\n","perf_df.plot(x=\"epoch\", y=[\"accuracy\", \"precision\", \"recall\", \"f1\"], kind=\"bar\", ax=ax)\n","\n","# add values on top of bars\n","for p in ax.patches:\n","    ax.annotate(\n","        f\"{p.get_height():.2f}\",\n","        (p.get_x() + p.get_width() / 2, p.get_height()),\n","        ha=\"center\",\n","        va=\"bottom\",\n","        fontsize=10,\n","    )\n","\n","# add title and labels\n","# ax.set_title(\"Metrics for different settings\")\n","# ax.set_ylabel(\"Value\")\n","ax.set_xlabel(\"Epoch (0: base model, 1-4: fine-tuned models)\")\n","# rotate x labels\n","plt.xticks(rotation=0)\n","\n","# set legend at the right to avoid overlapping with bars\n","plt.legend(loc=\"center left\", bbox_to_anchor=(1.0, 0.5))\n","# plt.tight_layout()\n","\n","plt.show()"]},{"cell_type":"code","execution_count":18,"metadata":{},"outputs":[],"source":["perf_df.to_csv(\"results/mgtv-results_p1_full_metrics.csv\", index=False)"]}],"metadata":{"accelerator":"GPU","application/vnd.databricks.v1+notebook":{"dashboards":[],"environmentMetadata":null,"language":"python","notebookMetadata":{"pythonIndentUnit":4},"notebookName":"07_MAC_+_Qwen2-7B-Instructi_Unsloth_train","widgets":{}},"colab":{"gpuType":"T4","provenance":[]},"kernelspec":{"display_name":"Python 3","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.11.9"}},"nbformat":4,"nbformat_minor":0}