{"cells":[{"cell_type":"code","execution_count":2,"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":3,"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":4,"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":5,"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":5,"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":6,"metadata":{},"outputs":[],"source":["P1 = \"\"\"你是一个逻辑游戏的主持人。游戏规则如下：\n","\n","1. 参与者会得到一个谜题。\n","2. 参与者可以通过提问来获取线索，尝试解开谜题。\n","3. 对于每个问题，主持人将根据实际情况回答以下五个选项之一：是、不是、不重要、回答正确、问法错误。\n","4. 回答中不能添加任何其它信息，也不能省略选项中的任何一个字。例如，不可以把“不是”省略成“不”。\n","5. 参与者需要根据回答来推理，并最终找出谜题的正确答案。\n","\n","请严格按照这些规则回答参与者提出的问题。\n","\n","谜题: {}\n","\n","实际情况: {}\n","\n","参与者提出的问题: {}\n","\"\"\""]},{"cell_type":"code","execution_count":7,"metadata":{},"outputs":[],"source":["P2 = \"\"\"你是一个情景猜谜游戏的主持人。游戏规则如下：\n","\n","1. 参与者会得到一个谜面，谜面会描述一个简单又难以理解的事件。\n","2. 主持人知道谜底，谜底是谜面的答案。\n","3. 参与者可以询问任何封闭式问题来找寻事件的真相。\n","4. 对于每个问题，主持人将根据实际情况回答以下五个选项之一：是、不是、不重要、回答正确、问法错误。各回答的判断标准如下：\n","   - 若谜面和谜底能找到问题的答案，回答：是或者不是\n","   - 若谜面和谜底不能直接或者间接推断出问题的答案，回答：不重要\n","   - 若参与者提问不是一个封闭式问题或者问题难以理解，回答：问法错误\n","   - 若参与者提问基本还原了谜底真相，回答：回答正确\n","5. 回答中不能添加任何其它信息，也不能省略选项中的任何一个字。例如，不可以把“不是”省略成“不”。\n","\n","请严格按照这些规则回答参与者提出的问题。\n","\n","**谜面:** {}\n","\n","**谜底:** {}\n","\n","**参与者提出的问题:** {}\n","\"\"\""]},{"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>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":9,"metadata":{},"output_type":"execute_result"}],"source":["import pandas as pd\n","\n","df_p1 = pd.read_csv(\"results/mgtv-results_p1_full_metrics.csv\")\n","df_p1"]},{"cell_type":"code","execution_count":10,"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>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>0.766000</td>\n","      <td>0.747969</td>\n","      <td>0.787526</td>\n","      <td>0.764922</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>1</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-88</td>\n","      <td>0.796333</td>\n","      <td>0.808232</td>\n","      <td>0.796333</td>\n","      <td>0.798160</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-176</td>\n","      <td>0.781333</td>\n","      <td>0.804716</td>\n","      <td>0.781333</td>\n","      <td>0.788581</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>3</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-264</td>\n","      <td>0.759000</td>\n","      <td>0.805502</td>\n","      <td>0.759000</td>\n","      <td>0.777237</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>4</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-352</td>\n","      <td>0.730333</td>\n","      <td>0.790676</td>\n","      <td>0.730333</td>\n","      <td>0.753716</td>\n","    </tr>\n","    <tr>\n","      <th>5</th>\n","      <td>5</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-440</td>\n","      <td>0.730333</td>\n","      <td>0.790420</td>\n","      <td>0.730333</td>\n","      <td>0.753750</td>\n","    </tr>\n","    <tr>\n","      <th>6</th>\n","      <td>6</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-528</td>\n","      <td>0.716000</td>\n","      <td>0.789892</td>\n","      <td>0.716000</td>\n","      <td>0.744833</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["   epoch                                           model  accuracy  precision  \\\n","0      0                 internlm/internlm2_5-7b-chat-1m  0.766000   0.747969   \n","1      1   internlm/internlm2_5-7b-chat-1m_checkpoint-88  0.796333   0.808232   \n","2      2  internlm/internlm2_5-7b-chat-1m_checkpoint-176  0.781333   0.804716   \n","3      3  internlm/internlm2_5-7b-chat-1m_checkpoint-264  0.759000   0.805502   \n","4      4  internlm/internlm2_5-7b-chat-1m_checkpoint-352  0.730333   0.790676   \n","5      5  internlm/internlm2_5-7b-chat-1m_checkpoint-440  0.730333   0.790420   \n","6      6  internlm/internlm2_5-7b-chat-1m_checkpoint-528  0.716000   0.789892   \n","\n","     recall        f1  \n","0  0.787526  0.764922  \n","1  0.796333  0.798160  \n","2  0.781333  0.788581  \n","3  0.759000  0.777237  \n","4  0.730333  0.753716  \n","5  0.730333  0.753750  \n","6  0.716000  0.744833  "]},"execution_count":10,"metadata":{},"output_type":"execute_result"}],"source":["df_p2 = pd.read_csv(\"results/mgtv-results_p2_full_metrics.csv\")\n","df_p2"]},{"cell_type":"code","execution_count":11,"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>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>0.766000</td>\n","      <td>0.747969</td>\n","      <td>0.787526</td>\n","      <td>0.764922</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>1</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-88</td>\n","      <td>0.796333</td>\n","      <td>0.808232</td>\n","      <td>0.796333</td>\n","      <td>0.798160</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-176</td>\n","      <td>0.781333</td>\n","      <td>0.804716</td>\n","      <td>0.781333</td>\n","      <td>0.788581</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>3</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-264</td>\n","      <td>0.759000</td>\n","      <td>0.805502</td>\n","      <td>0.759000</td>\n","      <td>0.777237</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>4</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-352</td>\n","      <td>0.730333</td>\n","      <td>0.790676</td>\n","      <td>0.730333</td>\n","      <td>0.753716</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["   epoch                                           model  accuracy  precision  \\\n","0      0                 internlm/internlm2_5-7b-chat-1m  0.766000   0.747969   \n","1      1   internlm/internlm2_5-7b-chat-1m_checkpoint-88  0.796333   0.808232   \n","2      2  internlm/internlm2_5-7b-chat-1m_checkpoint-176  0.781333   0.804716   \n","3      3  internlm/internlm2_5-7b-chat-1m_checkpoint-264  0.759000   0.805502   \n","4      4  internlm/internlm2_5-7b-chat-1m_checkpoint-352  0.730333   0.790676   \n","\n","     recall        f1  \n","0  0.787526  0.764922  \n","1  0.796333  0.798160  \n","2  0.781333  0.788581  \n","3  0.759000  0.777237  \n","4  0.730333  0.753716  "]},"execution_count":11,"metadata":{},"output_type":"execute_result"}],"source":["df_p2 = df_p2[:len(df_p1)]\n","df_p2"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[],"source":[]},{"cell_type":"code","execution_count":32,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["Best P1 accuracy:\n","0.7616666666666667\n","Best P2 accuracy:\n","0.7963333333333333\n"]},{"data":{"image/png":"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","text/plain":["<Figure size 1500x500 with 2 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["# plot the results\n","import matplotlib.pyplot as plt\n","import seaborn as sns\n","import matplotlib.ticker as ticker\n","\n","sns.set_theme(style=\"whitegrid\")\n","\n","# print the best results\n","best_p1 = df_p1[df_p1[\"accuracy\"] == df_p1[\"accuracy\"].max()]\n","best_p2 = df_p2[df_p2[\"accuracy\"] == df_p2[\"accuracy\"].max()]\n","\n","print(\"Best P1 accuracy:\")\n","print(best_p1[\"accuracy\"].values[0])\n","print(\"Best P2 accuracy:\")\n","print(best_p2[\"accuracy\"].values[0])\n","\n","# plot the best results\n","fig, ax = plt.subplots(1, 2, figsize=(15, 5))\n","\n","sns.lineplot(x=\"epoch\", y=\"accuracy\", data=df_p1, ax=ax[0], color=\"red\", label=\"P1\")\n","sns.lineplot(x=\"epoch\", y=\"accuracy\", data=df_p2, ax=ax[0], color=\"blue\", label=\"P2\")\n","sns.scatterplot(x=\"epoch\", y=\"accuracy\", data=best_p1, ax=ax[0], color=\"red\", s=50)\n","sns.scatterplot(x=\"epoch\", y=\"accuracy\", data=best_p2, ax=ax[0], color=\"blue\", s=50)\n","\n","sns.lineplot(x=\"epoch\", y=\"f1\", data=df_p1, ax=ax[1], color=\"red\", label=\"P1\")\n","sns.lineplot(x=\"epoch\", y=\"f1\", data=df_p2, ax=ax[1], color=\"blue\", label=\"P2\")\n","sns.scatterplot(x=\"epoch\", y=\"f1\", data=best_p1, ax=ax[1], color=\"red\", s=50)\n","sns.scatterplot(x=\"epoch\", y=\"f1\", data=best_p2, ax=ax[1], color=\"blue\", s=50)\n","\n","# plot values on the best results\n","ax[0].text(best_p1[\"epoch\"].values[0], best_p1[\"accuracy\"].values[0], round(best_p1[\"accuracy\"].values[0], 3), ha='left')\n","ax[0].text(best_p2[\"epoch\"].values[0], best_p2[\"accuracy\"].values[0], round(best_p2[\"accuracy\"].values[0], 3), ha='left')\n","ax[1].text(best_p1[\"epoch\"].values[0], best_p1[\"f1\"].values[0], round(best_p1[\"f1\"].values[0], 3), ha='left')\n","ax[1].text(best_p2[\"epoch\"].values[0], best_p2[\"f1\"].values[0], round(best_p2[\"f1\"].values[0], 3), ha='left')\n","\n","# plot values on epoch 0\n","ax[0].text(0, df_p1[\"accuracy\"].values[0], round(df_p1[\"accuracy\"].values[0], 3), ha='left')\n","ax[0].text(0, df_p2[\"accuracy\"].values[0], round(df_p2[\"accuracy\"].values[0], 3), ha='left')\n","ax[1].text(0, df_p1[\"f1\"].values[0], round(df_p1[\"f1\"].values[0], 3), ha='left')\n","ax[1].text(0, df_p2[\"f1\"].values[0], round(df_p2[\"f1\"].values[0], 3), ha='left')\n","\n","ax[0].set_title(\"Accuracy\")\n","ax[1].set_title(\"F1\")\n","\n","# After plotting your data and before plt.show(), add these lines\n","ax[0].xaxis.set_major_locator(ticker.MaxNLocator(integer=True))\n","ax[1].xaxis.set_major_locator(ticker.MaxNLocator(integer=True))\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}