competition/09c_InternLM_bf16_p2_analysis.ipynb

{"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":8,"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","    </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","    </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","    </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","    </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","    </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","    </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","    </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>不是</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","    </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","    </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","    </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","    </tr>\n","  </tbody>\n","</table>\n","<p>3000 rows × 9 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-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                                                  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-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","[3000 rows x 9 columns]"]},"execution_count":8,"metadata":{},"output_type":"execute_result"}],"source":["import pandas as pd\n","\n","df = pd.read_csv(\"results/mgtv-results_colab_p2.csv\")\n","df = clean_up(df, \"internlm/internlm2_5-7b-chat-1m\")\n","df"]},{"cell_type":"code","execution_count":9,"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":10,"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-562',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-1124',\n"," 'internlm/internlm2_5-7b-chat-1m_checkpoint-1686']"]},"execution_count":10,"metadata":{},"output_type":"execute_result"}],"source":["df.columns.to_list()"]},{"cell_type":"code","execution_count":11,"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-562 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-562\n","不重要     1799\n","是        817\n","不是       355\n","回答正确      24\n","问法错误       5\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-1124 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-1124\n","不是      1327\n","是       1147\n","不重要      494\n","问法错误      21\n","回答正确      11\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-1686 **********\n","internlm/internlm2_5-7b-chat-1m_checkpoint-1686\n","不是      1454\n","是        857\n","不重要      657\n","回答正确      18\n","问法错误      14\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":12,"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":13,"metadata":{},"outputs":[{"name":"stderr","output_type":"stream","text":["/var/folders/7x/56svhln929zdh2xhr3mwqg4r0000gn/T/ipykernel_38554/961288552.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-562</td>\n","      <td>0.398333</td>\n","      <td>0.835708</td>\n","      <td>0.398333</td>\n","      <td>0.477387</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-1124</td>\n","      <td>0.664667</td>\n","      <td>0.738958</td>\n","      <td>0.664667</td>\n","      <td>0.692464</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>3</td>\n","      <td>internlm/internlm2_5-7b-chat-1m_checkpoint-1686</td>\n","      <td>0.648000</td>\n","      <td>0.767207</td>\n","      <td>0.648000</td>\n","      <td>0.687518</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-562  0.398333   0.835708   \n","2     2  internlm/internlm2_5-7b-chat-1m_checkpoint-1124  0.664667   0.738958   \n","3     3  internlm/internlm2_5-7b-chat-1m_checkpoint-1686  0.648000   0.767207   \n","\n","     recall        f1  \n","0  0.781014  0.758887  \n","1  0.398333  0.477387  \n","2  0.664667  0.692464  \n","3  0.648000  0.687518  "]},"execution_count":13,"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":14,"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}