{"cells":[{"cell_type":"code","source":["%load_ext autoreload\n","%autoreload 2"],"metadata":{"id":"uWKRSV6eZsCn","executionInfo":{"status":"ok","timestamp":1720711613956,"user_tz":-480,"elapsed":2,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}},"colab":{"base_uri":"https://localhost:8080/"},"outputId":"10de0285-c19b-4aff-b2cd-b89e259adc47"},"execution_count":21,"outputs":[{"output_type":"stream","name":"stdout","text":["The autoreload extension is already loaded. To reload it, use:\n","  %reload_ext autoreload\n"]}]},{"cell_type":"code","execution_count":22,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"eb33b19f-1206-41ee-84e2-e6258a12eef7","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"id":"xwFh14uiZBrI","executionInfo":{"status":"ok","timestamp":1720711640125,"user_tz":-480,"elapsed":13209,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}},"outputId":"a308789f-8ca4-46ca-b535-a662dfb45082"},"outputs":[{"output_type":"stream","name":"stdout","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"]}],"source":["from google.colab import drive\n","drive.mount('/content/drive')"]},{"cell_type":"code","execution_count":23,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"6d394937-6c99-4a7c-9d32-7600a280032f","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"id":"G5pNu3zgZBrL","executionInfo":{"status":"ok","timestamp":1720711640125,"user_tz":-480,"elapsed":9,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}},"outputId":"e0f0ac3f-6bbb-4381-a527-5c679b67300f"},"outputs":[{"output_type":"stream","name":"stdout","text":["workding dir: /content/drive/MyDrive/logical-reasoning/\n"]}],"source":["import os\n","import sys\n","from pathlib import Path\n","\n","workding_dir = \"/content/drive/MyDrive/logical-reasoning/\"\n","os.chdir(workding_dir)\n","sys.path.append(workding_dir)\n","print(\"workding dir:\", workding_dir)"]},{"cell_type":"code","execution_count":24,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"ac667aba-076e-4de6-9984-8f6a67cb09cd","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"id":"0dVRAabNZBrL","executionInfo":{"status":"ok","timestamp":1720711640125,"user_tz":-480,"elapsed":7,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}},"outputId":"d97dd29b-ab43-4fc3-8e38-571280e598de"},"outputs":[{"output_type":"execute_result","data":{"text/plain":["False"]},"metadata":{},"execution_count":24}],"source":["need_to_setup_env = False\n","need_to_setup_env"]},{"cell_type":"code","execution_count":25,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"72f9cf79-7b0d-4d9e-90a0-1fa5251b947f","showTitle":false,"title":""},"id":"hKUOfP2HZBrL","executionInfo":{"status":"ok","timestamp":1720711640126,"user_tz":-480,"elapsed":7,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}}},"outputs":[],"source":["if need_to_setup_env:\n","    %pip install -r requirements.txt\n","    %cd /content/\n","    %rm -rf LLaMA-Factory\n","    !git clone https://github.com/hiyouga/LLaMA-Factory.git\n","    %cd LLaMA-Factory\n","    %ls\n","    %pip install -e .[torch,bitsandbytes]"]},{"cell_type":"code","execution_count":26,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"c06c61fd-4c6f-4099-bd3b-46188ab835d7","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"id":"txOgnjwYZBrL","executionInfo":{"status":"ok","timestamp":1720711640126,"user_tz":-480,"elapsed":7,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}},"outputId":"21f082c1-5cf8-4292-c18d-868f03fc5d8d"},"outputs":[{"output_type":"stream","name":"stdout","text":["workding dir: /content/drive/MyDrive/logical-reasoning/\n"]}],"source":["os.chdir(workding_dir)\n","sys.path.append(workding_dir)\n","print(\"workding dir:\", workding_dir)"]},{"cell_type":"code","execution_count":27,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"9f67ec60-2f24-411c-84eb-0dd664b44775","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"id":"hPCC-6m7ZBrM","executionInfo":{"status":"ok","timestamp":1720711640126,"user_tz":-480,"elapsed":7,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}},"outputId":"96d5a6cf-988d-4f21-dc30-bfeb52d61dd1"},"outputs":[{"output_type":"stream","name":"stdout","text":["loading env vars from: /content/drive/MyDrive/logical-reasoning/.env\n"]},{"output_type":"execute_result","data":{"text/plain":["True"]},"metadata":{},"execution_count":27}],"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":28,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"f1597656-8042-4878-9d3b-9ebfb8dd86dc","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"id":"1M3IraVtZBrM","executionInfo":{"status":"ok","timestamp":1720711640126,"user_tz":-480,"elapsed":6,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}},"outputId":"9f129c9e-7293-4c25-cca5-7ae4fdcab979"},"outputs":[{"output_type":"stream","name":"stdout","text":["internlm/internlm2_5-7b-chat-1m None True datasets/mgtv results/mgtv-results_colab_p2.csv False\n"]}],"source":["import os\n","\n","model_name = os.getenv(\"MODEL_NAME\")\n","adapter_name_or_path = os.getenv(\"ADAPTER_NAME_OR_PATH\")\n","load_in_4bit = os.getenv(\"LOAD_IN_4BIT\") == \"true\"\n","data_path = os.getenv(\"LOGICAL_REASONING_DATA_PATH\")\n","results_path = os.getenv(\"LOGICAL_REASONING_RESULTS_PATH\")\n","use_english_datasets = os.getenv(\"USE_ENGLISH_DATASETS\") == \"true\"\n","\n","print(model_name, adapter_name_or_path, load_in_4bit, data_path, results_path, use_english_datasets)"]},{"cell_type":"code","execution_count":29,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"e3ab54ba-7b6d-4817-bf2e-c5d711508b58","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"id":"mrVEz6UsZBrM","executionInfo":{"status":"ok","timestamp":1720711640126,"user_tz":-480,"elapsed":6,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}},"outputId":"57e472ec-cdee-47d3-b1da-5a5ca3e58131"},"outputs":[{"output_type":"stream","name":"stdout","text":["Thu Jul 11 15:27:19 2024       \n","+---------------------------------------------------------------------------------------+\n","| NVIDIA-SMI 535.104.05             Driver Version: 535.104.05   CUDA Version: 12.2     |\n","|-----------------------------------------+----------------------+----------------------+\n","| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |\n","| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |\n","|                                         |                      |               MIG M. |\n","|=========================================+======================+======================|\n","|   0  NVIDIA L4                      Off | 00000000:00:03.0 Off |                    0 |\n","| N/A   39C    P8              12W /  72W |      1MiB / 23034MiB |      0%      Default |\n","|                                         |                      |                  N/A |\n","+-----------------------------------------+----------------------+----------------------+\n","                                                                                         \n","+---------------------------------------------------------------------------------------+\n","| Processes:                                                                            |\n","|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |\n","|        ID   ID                                                             Usage      |\n","|=======================================================================================|\n","|  No running processes found                                                           |\n","+---------------------------------------------------------------------------------------+\n"]}],"source":["!nvidia-smi"]},{"cell_type":"code","execution_count":30,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"b2a43943-9324-4839-9a47-cfa72de2244b","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"id":"UgMvt6dIZBrM","executionInfo":{"status":"ok","timestamp":1720711640126,"user_tz":-480,"elapsed":5,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}},"outputId":"f7790506-b806-43ca-89eb-24c7f5471bfc"},"outputs":[{"output_type":"stream","name":"stdout","text":["Python 3.10.12\n","\u001b[33mWARNING: Package(s) not found: flash-attn\u001b[0m\u001b[33m\n","\u001b[0mCPU times: user 10.1 ms, sys: 1.94 ms, total: 12 ms\n","Wall time: 610 ms\n"]}],"source":["%%time\n","!python --version\n","!pip show flash-attn"]},{"cell_type":"code","execution_count":31,"metadata":{"id":"ZuS_FsLyZBrN","executionInfo":{"status":"ok","timestamp":1720711640126,"user_tz":-480,"elapsed":4,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}}},"outputs":[],"source":["from llm_toolkit.logical_reasoning_utils import *"]},{"cell_type":"code","execution_count":32,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":224},"id":"muFDE9DpZBrN","executionInfo":{"status":"ok","timestamp":1720711642271,"user_tz":-480,"elapsed":2149,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}},"outputId":"00ed5651-ae27-4292-a23c-f1c9952b9197"},"outputs":[{"output_type":"stream","name":"stdout","text":["loading existing data from: llama-factory/data/alpaca_mgtv_p2.json\n"]},{"output_type":"execute_result","data":{"text/plain":["                                         instruction input output\n","0  你是一个情景猜谜游戏的主持人。游戏规则如下：\\n\\n1. 参与者会得到一个谜面，谜面会描述一...           不是\n","1  你是一个情景猜谜游戏的主持人。游戏规则如下：\\n\\n1. 参与者会得到一个谜面，谜面会描述一...           不是\n","2  你是一个情景猜谜游戏的主持人。游戏规则如下：\\n\\n1. 参与者会得到一个谜面，谜面会描述一...          不重要\n","3  你是一个情景猜谜游戏的主持人。游戏规则如下：\\n\\n1. 参与者会得到一个谜面，谜面会描述一...           不是\n","4  你是一个情景猜谜游戏的主持人。游戏规则如下：\\n\\n1. 参与者会得到一个谜面，谜面会描述一...            是"],"text/html":["\n","  <div id=\"df-7131535b-9237-4312-8fe8-e50490ee1ed3\" class=\"colab-df-container\">\n","    <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>instruction</th>\n","      <th>input</th>\n","      <th>output</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>你是一个情景猜谜游戏的主持人。游戏规则如下：\\n\\n1. 参与者会得到一个谜面，谜面会描述一...</td>\n","      <td></td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>你是一个情景猜谜游戏的主持人。游戏规则如下：\\n\\n1. 参与者会得到一个谜面，谜面会描述一...</td>\n","      <td></td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>你是一个情景猜谜游戏的主持人。游戏规则如下：\\n\\n1. 参与者会得到一个谜面，谜面会描述一...</td>\n","      <td></td>\n","      <td>不重要</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>你是一个情景猜谜游戏的主持人。游戏规则如下：\\n\\n1. 参与者会得到一个谜面，谜面会描述一...</td>\n","      <td></td>\n","      <td>不是</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>你是一个情景猜谜游戏的主持人。游戏规则如下：\\n\\n1. 参与者会得到一个谜面，谜面会描述一...</td>\n","      <td></td>\n","      <td>是</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","    <div class=\"colab-df-buttons\">\n","\n","  <div class=\"colab-df-container\">\n","    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7131535b-9237-4312-8fe8-e50490ee1ed3')\"\n","            title=\"Convert this dataframe to an interactive table.\"\n","            style=\"display:none;\">\n","\n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n","    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n","  </svg>\n","    </button>\n","\n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    .colab-df-buttons div {\n","      margin-bottom: 4px;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","    <script>\n","      const buttonEl =\n","        document.querySelector('#df-7131535b-9237-4312-8fe8-e50490ee1ed3 button.colab-df-convert');\n","      buttonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n","      async function convertToInteractive(key) {\n","        const element = document.querySelector('#df-7131535b-9237-4312-8fe8-e50490ee1ed3');\n","        const dataTable =\n","          await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                    [key], {});\n","        if (!dataTable) return;\n","\n","        const docLinkHtml = 'Like what you see? Visit the ' +\n","          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","          + ' to learn more about interactive tables.';\n","        element.innerHTML = '';\n","        dataTable['output_type'] = 'display_data';\n","        await google.colab.output.renderOutput(dataTable, element);\n","        const docLink = document.createElement('div');\n","        docLink.innerHTML = docLinkHtml;\n","        element.appendChild(docLink);\n","      }\n","    </script>\n","  </div>\n","\n","\n","<div id=\"df-963e21ba-dc66-4cfb-b5b7-1e6bb91e2edf\">\n","  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-963e21ba-dc66-4cfb-b5b7-1e6bb91e2edf')\"\n","            title=\"Suggest charts\"\n","            style=\"display:none;\">\n","\n","<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","     width=\"24px\">\n","    <g>\n","        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n","    </g>\n","</svg>\n","  </button>\n","\n","<style>\n","  .colab-df-quickchart {\n","      --bg-color: #E8F0FE;\n","      --fill-color: #1967D2;\n","      --hover-bg-color: #E2EBFA;\n","      --hover-fill-color: #174EA6;\n","      --disabled-fill-color: #AAA;\n","      --disabled-bg-color: #DDD;\n","  }\n","\n","  [theme=dark] .colab-df-quickchart {\n","      --bg-color: #3B4455;\n","      --fill-color: #D2E3FC;\n","      --hover-bg-color: #434B5C;\n","      --hover-fill-color: #FFFFFF;\n","      --disabled-bg-color: #3B4455;\n","      --disabled-fill-color: #666;\n","  }\n","\n","  .colab-df-quickchart {\n","    background-color: var(--bg-color);\n","    border: none;\n","    border-radius: 50%;\n","    cursor: pointer;\n","    display: none;\n","    fill: var(--fill-color);\n","    height: 32px;\n","    padding: 0;\n","    width: 32px;\n","  }\n","\n","  .colab-df-quickchart:hover {\n","    background-color: var(--hover-bg-color);\n","    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n","    fill: var(--button-hover-fill-color);\n","  }\n","\n","  .colab-df-quickchart-complete:disabled,\n","  .colab-df-quickchart-complete:disabled:hover {\n","    background-color: var(--disabled-bg-color);\n","    fill: var(--disabled-fill-color);\n","    box-shadow: none;\n","  }\n","\n","  .colab-df-spinner {\n","    border: 2px solid var(--fill-color);\n","    border-color: transparent;\n","    border-bottom-color: var(--fill-color);\n","    animation:\n","      spin 1s steps(1) infinite;\n","  }\n","\n","  @keyframes spin {\n","    0% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","      border-left-color: var(--fill-color);\n","    }\n","    20% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    30% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","      border-right-color: var(--fill-color);\n","    }\n","    40% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    60% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","    }\n","    80% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-bottom-color: var(--fill-color);\n","    }\n","    90% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","    }\n","  }\n","</style>\n","\n","  <script>\n","    async function quickchart(key) {\n","      const quickchartButtonEl =\n","        document.querySelector('#' + key + ' button');\n","      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n","      quickchartButtonEl.classList.add('colab-df-spinner');\n","      try {\n","        const charts = await google.colab.kernel.invokeFunction(\n","            'suggestCharts', [key], {});\n","      } catch (error) {\n","        console.error('Error during call to suggestCharts:', error);\n","      }\n","      quickchartButtonEl.classList.remove('colab-df-spinner');\n","      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n","    }\n","    (() => {\n","      let quickchartButtonEl =\n","        document.querySelector('#df-963e21ba-dc66-4cfb-b5b7-1e6bb91e2edf button');\n","      quickchartButtonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","    })();\n","  </script>\n","</div>\n","\n","    </div>\n","  </div>\n"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"dataframe","variable_name":"df_alpaca","summary":"{\n  \"name\": \"df_alpaca\",\n  \"rows\": 25000,\n  \"fields\": [\n    {\n      \"column\": \"instruction\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 20112,\n        \"samples\": [\n          \"\\u4f60\\u662f\\u4e00\\u4e2a\\u60c5\\u666f\\u731c\\u8c1c\\u6e38\\u620f\\u7684\\u4e3b\\u6301\\u4eba\\u3002\\u6e38\\u620f\\u89c4\\u5219\\u5982\\u4e0b\\uff1a\\n\\n1. \\u53c2\\u4e0e\\u8005\\u4f1a\\u5f97\\u5230\\u4e00\\u4e2a\\u8c1c\\u9762\\uff0c\\u8c1c\\u9762\\u4f1a\\u63cf\\u8ff0\\u4e00\\u4e2a\\u7b80\\u5355\\u53c8\\u96be\\u4ee5\\u7406\\u89e3\\u7684\\u4e8b\\u4ef6\\u3002\\n2. \\u4e3b\\u6301\\u4eba\\u77e5\\u9053\\u8c1c\\u5e95\\uff0c\\u8c1c\\u5e95\\u662f\\u8c1c\\u9762\\u7684\\u7b54\\u6848\\u3002\\n3. \\u53c2\\u4e0e\\u8005\\u53ef\\u4ee5\\u8be2\\u95ee\\u4efb\\u4f55\\u5c01\\u95ed\\u5f0f\\u95ee\\u9898\\u6765\\u627e\\u5bfb\\u4e8b\\u4ef6\\u7684\\u771f\\u76f8\\u3002\\n4. \\u5bf9\\u4e8e\\u6bcf\\u4e2a\\u95ee\\u9898\\uff0c\\u4e3b\\u6301\\u4eba\\u5c06\\u6839\\u636e\\u5b9e\\u9645\\u60c5\\u51b5\\u56de\\u7b54\\u4ee5\\u4e0b\\u4e94\\u4e2a\\u9009\\u9879\\u4e4b\\u4e00\\uff1a\\u662f\\u3001\\u4e0d\\u662f\\u3001\\u4e0d\\u91cd\\u8981\\u3001\\u56de\\u7b54\\u6b63\\u786e\\u3001\\u95ee\\u6cd5\\u9519\\u8bef\\u3002\\u5404\\u56de\\u7b54\\u7684\\u5224\\u65ad\\u6807\\u51c6\\u5982\\u4e0b\\uff1a\\n   - \\u82e5\\u8c1c\\u9762\\u548c\\u8c1c\\u5e95\\u80fd\\u627e\\u5230\\u95ee\\u9898\\u7684\\u7b54\\u6848\\uff0c\\u56de\\u7b54\\uff1a\\u662f\\u6216\\u8005\\u4e0d\\u662f\\n   - \\u82e5\\u8c1c\\u9762\\u548c\\u8c1c\\u5e95\\u4e0d\\u80fd\\u76f4\\u63a5\\u6216\\u8005\\u95f4\\u63a5\\u63a8\\u65ad\\u51fa\\u95ee\\u9898\\u7684\\u7b54\\u6848\\uff0c\\u56de\\u7b54\\uff1a\\u4e0d\\u91cd\\u8981\\n   - \\u82e5\\u53c2\\u4e0e\\u8005\\u63d0\\u95ee\\u4e0d\\u662f\\u4e00\\u4e2a\\u5c01\\u95ed\\u5f0f\\u95ee\\u9898\\u6216\\u8005\\u95ee\\u9898\\u96be\\u4ee5\\u7406\\u89e3\\uff0c\\u56de\\u7b54\\uff1a\\u95ee\\u6cd5\\u9519\\u8bef\\n   - \\u82e5\\u53c2\\u4e0e\\u8005\\u63d0\\u95ee\\u57fa\\u672c\\u8fd8\\u539f\\u4e86\\u8c1c\\u5e95\\u771f\\u76f8\\uff0c\\u56de\\u7b54\\uff1a\\u56de\\u7b54\\u6b63\\u786e\\n5. \\u56de\\u7b54\\u4e2d\\u4e0d\\u80fd\\u6dfb\\u52a0\\u4efb\\u4f55\\u5176\\u5b83\\u4fe1\\u606f\\uff0c\\u4e5f\\u4e0d\\u80fd\\u7701\\u7565\\u9009\\u9879\\u4e2d\\u7684\\u4efb\\u4f55\\u4e00\\u4e2a\\u5b57\\u3002\\u4f8b\\u5982\\uff0c\\u4e0d\\u53ef\\u4ee5\\u628a\\u201c\\u4e0d\\u662f\\u201d\\u7701\\u7565\\u6210\\u201c\\u4e0d\\u201d\\u3002\\n\\n\\u8bf7\\u4e25\\u683c\\u6309\\u7167\\u8fd9\\u4e9b\\u89c4\\u5219\\u56de\\u7b54\\u53c2\\u4e0e\\u8005\\u63d0\\u51fa\\u7684\\u95ee\\u9898\\u3002\\n\\n**\\u8c1c\\u9762:** \\u5728\\u4e00\\u680b\\u8001\\u65e7\\u5c45\\u6c11\\u697c\\u7684\\u5730\\u4e0b\\u5ba4\\u3002\\u4e00\\u5929\\uff0c\\u8b66\\u65b9\\u63a5\\u5230\\u62a5\\u6848\\uff0c\\u6709\\u4eba\\u5728\\u5730\\u4e0b\\u5ba4\\u4e2d\\u53d1\\u73b0\\u4e86\\u7504\\u597d\\u5947\\u7684\\u9057\\u4f53\\u3002\\u73b0\\u573a\\u6ca1\\u6709\\u6253\\u6597\\u7684\\u75d5\\u8ff9\\uff0c\\u4e5f\\u6ca1\\u6709\\u660e\\u663e\\u7684\\u81ea\\u6740\\u5de5\\u5177\\u3002\\u6b7b\\u8005\\u88ab\\u53d1\\u73b0\\u65f6\\u5750\\u5728\\u4e00\\u628a\\u6905\\u5b50\\u4e0a\\uff0c\\u8868\\u60c5\\u5e73\\u9759\\uff0c\\u4f3c\\u4e4e\\u5728\\u6b7b\\u524d\\u5e76\\u672a\\u7ecf\\u5386\\u75db\\u82e6\\u3002\\u5730\\u4e0b\\u5ba4\\u9664\\u4e86\\u4e00\\u53f0\\u7535\\u89c6\\u548c\\u4e00\\u5f20\\u684c\\u5b50\\u5916\\uff0c\\u6ca1\\u6709\\u5176\\u4ed6\\u7269\\u54c1\\u3002\\u684c\\u4e0a\\u6709\\u4e00\\u676f\\u6c34\\uff0c\\u7535\\u89c6\\u8fd8\\u5f00\\u7740\\u3002\\u7a76\\u7adf\\u662f\\u4ec0\\u4e48\\u539f\\u56e0\\u5bfc\\u81f4\\u4e86\\u7504\\u597d\\u5947\\u7684\\u6b7b\\u4ea1\\uff1f\\n\\n**\\u8c1c\\u5e95:** \\u7504\\u597d\\u5947\\u5176\\u5b9e\\u662f\\u4e00\\u4f4d\\u79d1\\u5e7b\\u5c0f\\u8bf4\\u4f5c\\u5bb6\\uff0c\\u60a3\\u6709\\u4e25\\u91cd\\u7684\\u5e7d\\u95ed\\u6050\\u60e7\\u75c7\\u3002\\u4ed6\\u4e3a\\u4e86\\u5bfb\\u627e\\u5199\\u4f5c\\u7684\\u7075\\u611f\\uff0c\\u5e38\\u5e38\\u72ec\\u81ea\\u4e00\\u4eba\\u6765\\u5230\\u8fd9\\u4e2a\\u5730\\u4e0b\\u5ba4\\u89c2\\u770b\\u79d1\\u5e7b\\u7535\\u5f71\\u3002\\u4e0d\\u5e78\\u7684\\u662f\\uff0c\\u6709\\u4e00\\u5929\\u4ed6\\u5728\\u89c2\\u770b\\u7535\\u5f71\\u65f6\\u7a81\\u7136\\u906d\\u9047\\u505c\\u7535\\uff0c\\u5730\\u4e0b\\u5ba4\\u4e00\\u7247\\u6f06\\u9ed1\\u3002\\u4ed6\\u7684\\u5e7d\\u95ed\\u6050\\u60e7\\u75c7\\u53d1\\u4f5c\\uff0c\\u6781\\u5ea6\\u6050\\u614c\\u4e2d\\u8bef\\u4ee5\\u4e3a\\u81ea\\u5df1\\u88ab\\u56f0\\u5728\\u4e00\\u4e2a\\u672a\\u77e5\\u7684\\u5b87\\u5b99\\u7a7a\\u95f4\\u3002\\u5728\\u8fd9\\u79cd\\u6781\\u7aef\\u6050\\u60e7\\u7684\\u72b6\\u6001\\u4e0b\\uff0c\\u4ed6\\u7a81\\u53d1\\u5fc3\\u810f\\u75c5\\uff0c\\u5e73\\u9759\\u5730\\u79bb\\u5f00\\u4e86\\u4eba\\u4e16\\u3002\\u7531\\u4e8e\\u5fc3\\u810f\\u75c5\\u53d1\\u4f5c\\u65f6\\u6ca1\\u6709\\u75db\\u82e6\\uff0c\\u6240\\u4ee5\\u4ed6\\u7684\\u8868\\u60c5\\u770b\\u8d77\\u6765\\u5f88\\u5e73\\u9759\\u3002\\u800c\\u684c\\u4e0a\\u7684\\u6c34\\u548c\\u5f00\\u7740\\u7684\\u7535\\u89c6\\uff0c\\u53ea\\u662f\\u4ed6\\u65e5\\u5e38\\u5728\\u5730\\u4e0b\\u5ba4\\u5199\\u4f5c\\u65f6\\u7684\\u4e60\\u60ef\\u3002\\n\\n**\\u53c2\\u4e0e\\u8005\\u63d0\\u51fa\\u7684\\u95ee\\u9898:** \\u6c34\\u6709\\u6bd2\\n\",\n          \"\\u4f60\\u662f\\u4e00\\u4e2a\\u60c5\\u666f\\u731c\\u8c1c\\u6e38\\u620f\\u7684\\u4e3b\\u6301\\u4eba\\u3002\\u6e38\\u620f\\u89c4\\u5219\\u5982\\u4e0b\\uff1a\\n\\n1. \\u53c2\\u4e0e\\u8005\\u4f1a\\u5f97\\u5230\\u4e00\\u4e2a\\u8c1c\\u9762\\uff0c\\u8c1c\\u9762\\u4f1a\\u63cf\\u8ff0\\u4e00\\u4e2a\\u7b80\\u5355\\u53c8\\u96be\\u4ee5\\u7406\\u89e3\\u7684\\u4e8b\\u4ef6\\u3002\\n2. \\u4e3b\\u6301\\u4eba\\u77e5\\u9053\\u8c1c\\u5e95\\uff0c\\u8c1c\\u5e95\\u662f\\u8c1c\\u9762\\u7684\\u7b54\\u6848\\u3002\\n3. \\u53c2\\u4e0e\\u8005\\u53ef\\u4ee5\\u8be2\\u95ee\\u4efb\\u4f55\\u5c01\\u95ed\\u5f0f\\u95ee\\u9898\\u6765\\u627e\\u5bfb\\u4e8b\\u4ef6\\u7684\\u771f\\u76f8\\u3002\\n4. \\u5bf9\\u4e8e\\u6bcf\\u4e2a\\u95ee\\u9898\\uff0c\\u4e3b\\u6301\\u4eba\\u5c06\\u6839\\u636e\\u5b9e\\u9645\\u60c5\\u51b5\\u56de\\u7b54\\u4ee5\\u4e0b\\u4e94\\u4e2a\\u9009\\u9879\\u4e4b\\u4e00\\uff1a\\u662f\\u3001\\u4e0d\\u662f\\u3001\\u4e0d\\u91cd\\u8981\\u3001\\u56de\\u7b54\\u6b63\\u786e\\u3001\\u95ee\\u6cd5\\u9519\\u8bef\\u3002\\u5404\\u56de\\u7b54\\u7684\\u5224\\u65ad\\u6807\\u51c6\\u5982\\u4e0b\\uff1a\\n   - \\u82e5\\u8c1c\\u9762\\u548c\\u8c1c\\u5e95\\u80fd\\u627e\\u5230\\u95ee\\u9898\\u7684\\u7b54\\u6848\\uff0c\\u56de\\u7b54\\uff1a\\u662f\\u6216\\u8005\\u4e0d\\u662f\\n   - \\u82e5\\u8c1c\\u9762\\u548c\\u8c1c\\u5e95\\u4e0d\\u80fd\\u76f4\\u63a5\\u6216\\u8005\\u95f4\\u63a5\\u63a8\\u65ad\\u51fa\\u95ee\\u9898\\u7684\\u7b54\\u6848\\uff0c\\u56de\\u7b54\\uff1a\\u4e0d\\u91cd\\u8981\\n   - \\u82e5\\u53c2\\u4e0e\\u8005\\u63d0\\u95ee\\u4e0d\\u662f\\u4e00\\u4e2a\\u5c01\\u95ed\\u5f0f\\u95ee\\u9898\\u6216\\u8005\\u95ee\\u9898\\u96be\\u4ee5\\u7406\\u89e3\\uff0c\\u56de\\u7b54\\uff1a\\u95ee\\u6cd5\\u9519\\u8bef\\n   - \\u82e5\\u53c2\\u4e0e\\u8005\\u63d0\\u95ee\\u57fa\\u672c\\u8fd8\\u539f\\u4e86\\u8c1c\\u5e95\\u771f\\u76f8\\uff0c\\u56de\\u7b54\\uff1a\\u56de\\u7b54\\u6b63\\u786e\\n5. \\u56de\\u7b54\\u4e2d\\u4e0d\\u80fd\\u6dfb\\u52a0\\u4efb\\u4f55\\u5176\\u5b83\\u4fe1\\u606f\\uff0c\\u4e5f\\u4e0d\\u80fd\\u7701\\u7565\\u9009\\u9879\\u4e2d\\u7684\\u4efb\\u4f55\\u4e00\\u4e2a\\u5b57\\u3002\\u4f8b\\u5982\\uff0c\\u4e0d\\u53ef\\u4ee5\\u628a\\u201c\\u4e0d\\u662f\\u201d\\u7701\\u7565\\u6210\\u201c\\u4e0d\\u201d\\u3002\\n\\n\\u8bf7\\u4e25\\u683c\\u6309\\u7167\\u8fd9\\u4e9b\\u89c4\\u5219\\u56de\\u7b54\\u53c2\\u4e0e\\u8005\\u63d0\\u51fa\\u7684\\u95ee\\u9898\\u3002\\n\\n**\\u8c1c\\u9762:** \\u5728\\u4e00\\u4e2a\\u5bc2\\u9759\\u7684\\u591c\\u665a\\uff0c\\u7504\\u8d3e\\u8d3e\\u5306\\u5306\\u5fd9\\u5fd9\\u5730\\u4ece\\u5c0f\\u5df7\\u5b50\\u91cc\\u8dd1\\u4e86\\u51fa\\u6765\\uff0c\\u8138\\u4e0a\\u6ee1\\u662f\\u60ca\\u6050\\u3002\\u5728\\u4ed6\\u8eab\\u540e\\uff0c\\u4e00\\u53ea\\u7a7a\\u8361\\u8361\\u7684\\u5783\\u573e\\u6876\\u7ffb\\u5012\\u5728\\u5730\\u3002\\u7504\\u8d3e\\u8d3e\\u5e76\\u975e\\u5c0f\\u5df7\\u91cc\\u7684\\u5c45\\u6c11\\uff0c\\u4e5f\\u6ca1\\u6709\\u4e0e\\u4eba\\u7ed3\\u6028\\u3002\\u7a76\\u7adf\\u662f\\u4ec0\\u4e48\\u539f\\u56e0\\u8ba9\\u4ed6\\u5982\\u6b64\\u60ca\\u614c\\u5931\\u63aa\\uff1f\\n\\n**\\u8c1c\\u5e95:** \\u539f\\u6765\\uff0c\\u7504\\u8d3e\\u8d3e\\u662f\\u4e00\\u540d\\u6b63\\u5728\\u6f5c\\u9003\\u7684\\u5c0f\\u5077\\u3002\\u5f53\\u665a\\uff0c\\u4ed6\\u4f01\\u56fe\\u5728\\u5df7\\u5b50\\u91cc\\u5bfb\\u627e\\u53ef\\u4ee5\\u76d7\\u7a83\\u7684\\u76ee\\u6807\\uff0c\\u5374\\u4e0d\\u6599\\u5783\\u573e\\u6876\\u91cc\\u7a81\\u7136\\u7a9c\\u51fa\\u4e00\\u53ea\\u91ce\\u732b\\uff0c\\u5c06\\u4ed6\\u5413\\u4e86\\u4e00\\u8df3\\u3002\\u4ed6\\u4ee5\\u4e3a\\u662f\\u88ab\\u8b66\\u65b9\\u53d1\\u73b0\\u4e86\\uff0c\\u4e8e\\u662f\\u60ca\\u614c\\u5931\\u63aa\\u5730\\u9003\\u8dd1\\u4e86\\u3002\\u800c\\u90a3\\u53ea\\u5783\\u573e\\u6876\\uff0c\\u6b63\\u662f\\u4ed6\\u7ffb\\u627e\\u4e1c\\u897f\\u65f6\\u4e0d\\u5c0f\\u5fc3\\u5f04\\u7ffb\\u7684\\u3002\\n\\n**\\u53c2\\u4e0e\\u8005\\u63d0\\u51fa\\u7684\\u95ee\\u9898:** \\u4ed6\\u770b\\u5230\\u4e86\\u4e0d\\u8be5\\u770b\\u7684\\u4e1c\\u897f\\u5417\\n\",\n          \"\\u4f60\\u662f\\u4e00\\u4e2a\\u60c5\\u666f\\u731c\\u8c1c\\u6e38\\u620f\\u7684\\u4e3b\\u6301\\u4eba\\u3002\\u6e38\\u620f\\u89c4\\u5219\\u5982\\u4e0b\\uff1a\\n\\n1. \\u53c2\\u4e0e\\u8005\\u4f1a\\u5f97\\u5230\\u4e00\\u4e2a\\u8c1c\\u9762\\uff0c\\u8c1c\\u9762\\u4f1a\\u63cf\\u8ff0\\u4e00\\u4e2a\\u7b80\\u5355\\u53c8\\u96be\\u4ee5\\u7406\\u89e3\\u7684\\u4e8b\\u4ef6\\u3002\\n2. \\u4e3b\\u6301\\u4eba\\u77e5\\u9053\\u8c1c\\u5e95\\uff0c\\u8c1c\\u5e95\\u662f\\u8c1c\\u9762\\u7684\\u7b54\\u6848\\u3002\\n3. \\u53c2\\u4e0e\\u8005\\u53ef\\u4ee5\\u8be2\\u95ee\\u4efb\\u4f55\\u5c01\\u95ed\\u5f0f\\u95ee\\u9898\\u6765\\u627e\\u5bfb\\u4e8b\\u4ef6\\u7684\\u771f\\u76f8\\u3002\\n4. \\u5bf9\\u4e8e\\u6bcf\\u4e2a\\u95ee\\u9898\\uff0c\\u4e3b\\u6301\\u4eba\\u5c06\\u6839\\u636e\\u5b9e\\u9645\\u60c5\\u51b5\\u56de\\u7b54\\u4ee5\\u4e0b\\u4e94\\u4e2a\\u9009\\u9879\\u4e4b\\u4e00\\uff1a\\u662f\\u3001\\u4e0d\\u662f\\u3001\\u4e0d\\u91cd\\u8981\\u3001\\u56de\\u7b54\\u6b63\\u786e\\u3001\\u95ee\\u6cd5\\u9519\\u8bef\\u3002\\u5404\\u56de\\u7b54\\u7684\\u5224\\u65ad\\u6807\\u51c6\\u5982\\u4e0b\\uff1a\\n   - \\u82e5\\u8c1c\\u9762\\u548c\\u8c1c\\u5e95\\u80fd\\u627e\\u5230\\u95ee\\u9898\\u7684\\u7b54\\u6848\\uff0c\\u56de\\u7b54\\uff1a\\u662f\\u6216\\u8005\\u4e0d\\u662f\\n   - \\u82e5\\u8c1c\\u9762\\u548c\\u8c1c\\u5e95\\u4e0d\\u80fd\\u76f4\\u63a5\\u6216\\u8005\\u95f4\\u63a5\\u63a8\\u65ad\\u51fa\\u95ee\\u9898\\u7684\\u7b54\\u6848\\uff0c\\u56de\\u7b54\\uff1a\\u4e0d\\u91cd\\u8981\\n   - \\u82e5\\u53c2\\u4e0e\\u8005\\u63d0\\u95ee\\u4e0d\\u662f\\u4e00\\u4e2a\\u5c01\\u95ed\\u5f0f\\u95ee\\u9898\\u6216\\u8005\\u95ee\\u9898\\u96be\\u4ee5\\u7406\\u89e3\\uff0c\\u56de\\u7b54\\uff1a\\u95ee\\u6cd5\\u9519\\u8bef\\n   - \\u82e5\\u53c2\\u4e0e\\u8005\\u63d0\\u95ee\\u57fa\\u672c\\u8fd8\\u539f\\u4e86\\u8c1c\\u5e95\\u771f\\u76f8\\uff0c\\u56de\\u7b54\\uff1a\\u56de\\u7b54\\u6b63\\u786e\\n5. \\u56de\\u7b54\\u4e2d\\u4e0d\\u80fd\\u6dfb\\u52a0\\u4efb\\u4f55\\u5176\\u5b83\\u4fe1\\u606f\\uff0c\\u4e5f\\u4e0d\\u80fd\\u7701\\u7565\\u9009\\u9879\\u4e2d\\u7684\\u4efb\\u4f55\\u4e00\\u4e2a\\u5b57\\u3002\\u4f8b\\u5982\\uff0c\\u4e0d\\u53ef\\u4ee5\\u628a\\u201c\\u4e0d\\u662f\\u201d\\u7701\\u7565\\u6210\\u201c\\u4e0d\\u201d\\u3002\\n\\n\\u8bf7\\u4e25\\u683c\\u6309\\u7167\\u8fd9\\u4e9b\\u89c4\\u5219\\u56de\\u7b54\\u53c2\\u4e0e\\u8005\\u63d0\\u51fa\\u7684\\u95ee\\u9898\\u3002\\n\\n**\\u8c1c\\u9762:** \\u5728\\u4e00\\u4e2a\\u5bc2\\u9759\\u7684\\u591c\\u665a\\uff0c\\u7504\\u8d3e\\u8d3e\\u5306\\u5306\\u5fd9\\u5fd9\\u5730\\u4ece\\u5c0f\\u5df7\\u5b50\\u91cc\\u8dd1\\u4e86\\u51fa\\u6765\\uff0c\\u8138\\u4e0a\\u6ee1\\u662f\\u60ca\\u6050\\u3002\\u5728\\u4ed6\\u8eab\\u540e\\uff0c\\u4e00\\u53ea\\u7a7a\\u8361\\u8361\\u7684\\u5783\\u573e\\u6876\\u7ffb\\u5012\\u5728\\u5730\\u3002\\u7504\\u8d3e\\u8d3e\\u5e76\\u975e\\u5c0f\\u5df7\\u91cc\\u7684\\u5c45\\u6c11\\uff0c\\u4e5f\\u6ca1\\u6709\\u4e0e\\u4eba\\u7ed3\\u6028\\u3002\\u7a76\\u7adf\\u662f\\u4ec0\\u4e48\\u539f\\u56e0\\u8ba9\\u4ed6\\u5982\\u6b64\\u60ca\\u614c\\u5931\\u63aa\\uff1f\\n\\n**\\u8c1c\\u5e95:** \\u539f\\u6765\\uff0c\\u7504\\u8d3e\\u8d3e\\u662f\\u4e00\\u540d\\u6b63\\u5728\\u6f5c\\u9003\\u7684\\u5c0f\\u5077\\u3002\\u5f53\\u665a\\uff0c\\u4ed6\\u4f01\\u56fe\\u5728\\u5df7\\u5b50\\u91cc\\u5bfb\\u627e\\u53ef\\u4ee5\\u76d7\\u7a83\\u7684\\u76ee\\u6807\\uff0c\\u5374\\u4e0d\\u6599\\u5783\\u573e\\u6876\\u91cc\\u7a81\\u7136\\u7a9c\\u51fa\\u4e00\\u53ea\\u91ce\\u732b\\uff0c\\u5c06\\u4ed6\\u5413\\u4e86\\u4e00\\u8df3\\u3002\\u4ed6\\u4ee5\\u4e3a\\u662f\\u88ab\\u8b66\\u65b9\\u53d1\\u73b0\\u4e86\\uff0c\\u4e8e\\u662f\\u60ca\\u614c\\u5931\\u63aa\\u5730\\u9003\\u8dd1\\u4e86\\u3002\\u800c\\u90a3\\u53ea\\u5783\\u573e\\u6876\\uff0c\\u6b63\\u662f\\u4ed6\\u7ffb\\u627e\\u4e1c\\u897f\\u65f6\\u4e0d\\u5c0f\\u5fc3\\u5f04\\u7ffb\\u7684\\u3002\\n\\n**\\u53c2\\u4e0e\\u8005\\u63d0\\u51fa\\u7684\\u95ee\\u9898:** \\u6d41\\u6d6a\\u732b\\u5417\\uff1f\\n\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"input\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 1,\n        \"samples\": [\n          \"\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"output\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"\\u4e0d\\u91cd\\u8981\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"}},"metadata":{},"execution_count":32}],"source":["df_alpaca = load_alpaca_data(data_path, using_p1=False)\n","df_alpaca.head()"]},{"source":["# @title output\n","\n","from matplotlib import pyplot as plt\n","import seaborn as sns\n","df_alpaca.groupby('output').size().plot(kind='barh', color=sns.palettes.mpl_palette('Dark2'))\n","plt.gca().spines[['top', 'right',]].set_visible(False)"],"cell_type":"code","execution_count":33,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 19981 (\\N{CJK UNIFIED IDEOGRAPH-4E0D}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 26159 (\\N{CJK UNIFIED IDEOGRAPH-662F}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 37325 (\\N{CJK UNIFIED IDEOGRAPH-91CD}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 35201 (\\N{CJK UNIFIED IDEOGRAPH-8981}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 22238 (\\N{CJK UNIFIED IDEOGRAPH-56DE}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 31572 (\\N{CJK UNIFIED IDEOGRAPH-7B54}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 27491 (\\N{CJK UNIFIED IDEOGRAPH-6B63}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 30830 (\\N{CJK UNIFIED IDEOGRAPH-786E}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 38382 (\\N{CJK UNIFIED IDEOGRAPH-95EE}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 27861 (\\N{CJK UNIFIED IDEOGRAPH-6CD5}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 38169 (\\N{CJK UNIFIED IDEOGRAPH-9519}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/events.py:89: UserWarning: Glyph 35823 (\\N{CJK UNIFIED IDEOGRAPH-8BEF}) missing from current font.\n","  func(*args, **kwargs)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 19981 (\\N{CJK UNIFIED IDEOGRAPH-4E0D}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 26159 (\\N{CJK UNIFIED IDEOGRAPH-662F}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 37325 (\\N{CJK UNIFIED IDEOGRAPH-91CD}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 35201 (\\N{CJK UNIFIED IDEOGRAPH-8981}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 22238 (\\N{CJK UNIFIED IDEOGRAPH-56DE}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 31572 (\\N{CJK UNIFIED IDEOGRAPH-7B54}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 27491 (\\N{CJK UNIFIED IDEOGRAPH-6B63}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 30830 (\\N{CJK UNIFIED IDEOGRAPH-786E}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 38382 (\\N{CJK UNIFIED IDEOGRAPH-95EE}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 27861 (\\N{CJK UNIFIED IDEOGRAPH-6CD5}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 38169 (\\N{CJK UNIFIED IDEOGRAPH-9519}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n","/usr/local/lib/python3.10/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 35823 (\\N{CJK UNIFIED IDEOGRAPH-8BEF}) missing from current font.\n","  fig.canvas.print_figure(bytes_io, **kw)\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}}],"metadata":{"cellView":"form","colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"_ofVQITbZiTI","executionInfo":{"status":"ok","timestamp":1720711642271,"user_tz":-480,"elapsed":8,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"}},"outputId":"9c08e305-5e54-4a62-8ed7-4bdf78e1866f"}},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"xPVpy6WpZBrN","outputId":"b5dc593a-8da5-4dfb-e056-192d0325f299"},"outputs":[{"output_type":"stream","name":"stdout","text":["Current Directory:\n","/content/drive/MyDrive/logical-reasoning/llama-factory\n","config/internlm2_5_7b_lora_sft_bf16_p2.yaml:\n"," {\n","  \"model_name_or_path\": \"internlm/internlm2_5-7b-chat-1m\",\n","  \"stage\": \"sft\",\n","  \"do_train\": true,\n","  \"finetuning_type\": \"lora\",\n","  \"lora_target\": \"all\",\n","  \"loraplus_lr_ratio\": 16.0,\n","  \"upcast_layernorm\": true,\n","  \"dataset\": \"alpaca_mgtv_p2\",\n","  \"template\": \"chatml\",\n","  \"cutoff_len\": 1024,\n","  \"max_samples\": 5000,\n","  \"overwrite_cache\": true,\n","  \"preprocessing_num_workers\": 16,\n","  \"output_dir\": \"saves/internlm2_5_7b/lora/sft_bf16_p2\",\n","  \"logging_steps\": 100,\n","  \"save_steps\": 562,\n","  \"plot_loss\": true,\n","  \"overwrite_output_dir\": true,\n","  \"per_device_train_batch_size\": 1,\n","  \"gradient_accumulation_steps\": 8,\n","  \"learning_rate\": 0.0001,\n","  \"num_train_epochs\": 4.0,\n","  \"lr_scheduler_type\": \"cosine\",\n","  \"warmup_ratio\": 0.1,\n","  \"bf16\": true,\n","  \"ddp_timeout\": 180000000,\n","  \"val_size\": 0.1,\n","  \"per_device_eval_batch_size\": 1,\n","  \"eval_strategy\": \"steps\",\n","  \"eval_steps\": 562,\n","  \"report_to\": \"wandb\",\n","  \"run_name\": \"internlm2_5_7b\"\n","}\n","2024-07-11 15:27:28.654916: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n","2024-07-11 15:27:28.706836: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n","2024-07-11 15:27:28.706879: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n","2024-07-11 15:27:28.708441: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n","2024-07-11 15:27:28.716261: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n","To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n","2024-07-11 15:27:29.959219: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n","07/11/2024 15:27:37 - INFO - llamafactory.hparams.parser - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.bfloat16\n","tokenizer_config.json: 100% 2.51k/2.51k [00:00<00:00, 17.1MB/s]\n","tokenization_internlm2_fast.py: 100% 7.80k/7.80k [00:00<00:00, 37.5MB/s]\n","tokenization_internlm2.py: 100% 8.81k/8.81k [00:00<00:00, 42.6MB/s]\n","tokenizer.model: 100% 1.48M/1.48M [00:00<00:00, 123MB/s]\n","special_tokens_map.json: 100% 713/713 [00:00<00:00, 4.85MB/s]\n","[INFO|tokenization_utils_base.py:2108] 2024-07-11 15:27:41,196 >> loading file ./tokenizer.model from cache at /root/.cache/huggingface/hub/models--internlm--internlm2_5-7b-chat-1m/snapshots/8d1a709a04d71440ef3df6ebbe204672f411c8b6/./tokenizer.model\n","[INFO|tokenization_utils_base.py:2108] 2024-07-11 15:27:41,196 >> loading file added_tokens.json from cache at None\n","[INFO|tokenization_utils_base.py:2108] 2024-07-11 15:27:41,196 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--internlm--internlm2_5-7b-chat-1m/snapshots/8d1a709a04d71440ef3df6ebbe204672f411c8b6/special_tokens_map.json\n","[INFO|tokenization_utils_base.py:2108] 2024-07-11 15:27:41,196 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--internlm--internlm2_5-7b-chat-1m/snapshots/8d1a709a04d71440ef3df6ebbe204672f411c8b6/tokenizer_config.json\n","[INFO|tokenization_utils_base.py:2108] 2024-07-11 15:27:41,196 >> loading file tokenizer.json from cache at None\n","07/11/2024 15:27:42 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>\n","07/11/2024 15:27:42 - INFO - llamafactory.data.template - Add <|im_start|> to stop words.\n","07/11/2024 15:27:43 - INFO - llamafactory.data.loader - Loading dataset alpaca_mgtv_p2.json...\n","Generating train split: 25000 examples [00:00, 35807.97 examples/s]\n","/usr/local/lib/python3.10/dist-packages/multiprocess/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.\n","  self.pid = os.fork()\n","Converting format of dataset (num_proc=16): 100% 5000/5000 [00:00<00:00, 20104.28 examples/s]\n","Running tokenizer on dataset (num_proc=16): 100% 5000/5000 [00:02<00:00, 1757.57 examples/s]\n","input_ids:\n","[92543, 1008, 364, 60403, 68625, 77794, 62591, 63352, 68309, 69323, 60687, 60364, 60355, 68309, 69776, 68411, 60387, 402, 312, 281, 262, 69102, 60497, 60382, 89428, 63352, 60388, 60353, 63352, 60388, 60382, 69401, 68252, 87114, 70436, 68865, 82168, 60355, 364, 314, 281, 262, 74243, 68290, 63352, 60930, 60353, 63352, 60930, 60357, 63352, 68421, 69059, 60355, 364, 308, 281, 262, 69102, 60497, 68251, 73477, 68574, 74004, 60550, 68287, 89214, 61683, 88840, 73687, 60355, 364, 319, 281, 262, 68390, 68772, 68287, 60353, 74243, 60530, 68420, 74740, 68855, 68544, 72719, 68423, 68538, 60387, 60357, 60359, 68278, 60359, 82568, 60359, 68855, 69077, 60359, 60593, 60408, 69583, 60355, 60684, 68855, 60354, 69844, 68559, 68411, 60387, 364, 393, 285, 262, 61369, 63352, 81953, 63352, 60930, 91085, 70670, 69059, 60353, 68855, 60387, 60357, 68319, 68278, 364, 393, 285, 262, 61369, 63352, 81953, 63352, 60930, 68336, 68376, 68319, 80078, 60876, 61015, 60389, 70670, 69059, 60353, 68855, 60387, 82568, 364, 393, 285, 262, 61369, 69102, 60497, 73912, 79865, 74004, 60550, 68287, 68319, 68287, 70436, 68865, 60353, 68855, 60387, 60593, 60408, 69583, 364, 393, 285, 262, 61369, 69102, 60497, 73912, 68406, 71940, 60362, 63352, 60930, 73687, 60353, 68855, 60387, 68855, 69077, 364, 317, 281, 262, 68855, 60366, 68336, 68535, 68574, 69344, 68347, 60353, 71452, 81256, 68423, 68322, 78818, 60666, 60355, 69192, 60353, 73263, 60581, 60419, 68278, 60420, 81256, 60397, 60419, 60358, 60420, 60355, 402, 60836, 86910, 68374, 69776, 68855, 69102, 60497, 74743, 68287, 60355, 402, 465, 63352, 60388, 334, 465, 262, 60361, 63840, 60396, 78165, 60353, 68935, 79406, 70952, 60387, 69731, 71150, 88982, 82620, 60353, 71150, 61329, 60425, 60649, 68935, 69410, 71150, 60382, 60358, 62273, 60458, 61217, 60353, 71479, 60400, 72593, 69380, 79594, 90209, 60355, 60836, 75326, 71150, 82066, 79202, 68540, 60355, 402, 465, 63352, 60930, 334, 465, 262, 73687, 69607, 60510, 70226, 60372, 62650, 60354, 61044, 61066, 69045, 60355, 71389, 61044, 61066, 89463, 60353, 61002, 60510, 70226, 73027, 70134, 60544, 61422, 60355, 68310, 74907, 60361, 71150, 88982, 82620, 68980, 60355, 69104, 60353, 71062, 61976, 60364, 60353, 70134, 60361, 72325, 60463, 68294, 60612, 70623, 60366, 60877, 60668, 60355, 74726, 60354, 61044, 61066, 68394, 70367, 60447, 69126, 70134, 60353, 69731, 68549, 60530, 69410, 71150, 61882, 60825, 60353, 70395, 70134, 60354, 62296, 60463, 60353, 72069, 86407, 68304, 63024, 60880, 60355, 68597, 68891, 73936, 60362, 69372, 60353, 71093, 72276, 60425, 68252, 82569, 70952, 60355, 402, 465, 69102, 60497, 74743, 68287, 334, 465, 262, 61882, 68279, 60548, 60780, 61076, 364, 92542, 364, 92543, 525, 11353, 364, 68278, 92542]\n","inputs:\n","<|im_start|>user\n","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:** 在甄家村里，有一个古老的传说：每年南瓜丰收的季节，南瓜田里总有一个最大的南瓜会不翼而飞，村民们对此现象困惑不解。请找出南瓜失踪背后的原因。\n","\n","**谜底:** 真相原来与一位年迈的农夫有关。这位农夫年轻时，曾与一位美丽的姑娘相恋。他们约定在南瓜丰收的季节结婚。然而，命运弄人，姑娘在婚礼前的一场意外中离世。悲伤的农夫为了纪念心爱的姑娘，每年都会将最大的南瓜偷走，放到姑娘的墓前，以此寄托自己的哀思。这一行为延续了多年，成为了乡村里一个神秘的传说。\n","\n","**参与者提出的问题:** 偷的人信神吗\n","<|im_end|>\n","<|im_start|>assistant\n","不是<|im_end|>\n","label_ids:\n","[-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 68278, 92542]\n","labels:\n","不是<|im_end|>\n","/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n","  warnings.warn(\n","config.json: 100% 895/895 [00:00<00:00, 6.35MB/s]\n","[INFO|configuration_utils.py:733] 2024-07-11 15:27:48,939 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--internlm--internlm2_5-7b-chat-1m/snapshots/8d1a709a04d71440ef3df6ebbe204672f411c8b6/config.json\n","configuration_internlm2.py: 100% 8.84k/8.84k [00:00<00:00, 39.3MB/s]\n","[INFO|configuration_utils.py:733] 2024-07-11 15:27:49,809 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--internlm--internlm2_5-7b-chat-1m/snapshots/8d1a709a04d71440ef3df6ebbe204672f411c8b6/config.json\n","[INFO|configuration_utils.py:796] 2024-07-11 15:27:49,810 >> Model config InternLM2Config {\n","  \"_name_or_path\": \"internlm/internlm2_5-7b-chat-1m\",\n","  \"architectures\": [\n","    \"InternLM2ForCausalLM\"\n","  ],\n","  \"attn_implementation\": \"eager\",\n","  \"auto_map\": {\n","    \"AutoConfig\": \"internlm/internlm2_5-7b-chat-1m--configuration_internlm2.InternLM2Config\",\n","    \"AutoModel\": \"internlm/internlm2_5-7b-chat-1m--modeling_internlm2.InternLM2ForCausalLM\",\n","    \"AutoModelForCausalLM\": \"internlm/internlm2_5-7b-chat-1m--modeling_internlm2.InternLM2ForCausalLM\"\n","  },\n","  \"bias\": false,\n","  \"bos_token_id\": 1,\n","  \"eos_token_id\": 2,\n","  \"hidden_act\": \"silu\",\n","  \"hidden_size\": 4096,\n","  \"initializer_range\": 0.02,\n","  \"intermediate_size\": 14336,\n","  \"max_position_embeddings\": 262144,\n","  \"model_type\": \"internlm2\",\n","  \"num_attention_heads\": 32,\n","  \"num_hidden_layers\": 32,\n","  \"num_key_value_heads\": 8,\n","  \"pad_token_id\": 2,\n","  \"pretraining_tp\": 1,\n","  \"rms_norm_eps\": 1e-05,\n","  \"rope_scaling\": {\n","    \"factor\": 2.5,\n","    \"type\": \"dynamic\"\n","  },\n","  \"rope_theta\": 50000000,\n","  \"tie_word_embeddings\": false,\n","  \"torch_dtype\": \"bfloat16\",\n","  \"transformers_version\": \"4.41.2\",\n","  \"use_cache\": true,\n","  \"vocab_size\": 92544\n","}\n","\n","modeling_internlm2.py: 100% 80.7k/80.7k [00:00<00:00, 363kB/s]\n","model.safetensors.index.json: 100% 18.2k/18.2k [00:00<00:00, 76.9MB/s]\n","[INFO|modeling_utils.py:3474] 2024-07-11 15:27:51,751 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--internlm--internlm2_5-7b-chat-1m/snapshots/8d1a709a04d71440ef3df6ebbe204672f411c8b6/model.safetensors.index.json\n","Downloading shards:   0% 0/8 [00:00<?, ?it/s]\n","model-00001-of-00008.safetensors:   0% 0.00/1.95G [00:00<?, ?B/s]\u001b[A\n","model-00001-of-00008.safetensors:   1% 10.5M/1.95G [00:00<00:43, 44.4MB/s]\u001b[A\n","model-00001-of-00008.safetensors:   3% 52.4M/1.95G [00:00<00:10, 174MB/s] \u001b[A\n","model-00001-of-00008.safetensors:   5% 94.4M/1.95G [00:00<00:07, 239MB/s]\u001b[A\n","model-00001-of-00008.safetensors:   6% 126M/1.95G [00:00<00:07, 258MB/s] \u001b[A\n","model-00001-of-00008.safetensors:   9% 168M/1.95G [00:00<00:06, 281MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  10% 199M/1.95G [00:00<00:06, 289MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  12% 231M/1.95G [00:00<00:06, 278MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  14% 273M/1.95G [00:01<00:05, 283MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  16% 304M/1.95G [00:01<00:06, 272MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  17% 336M/1.95G [00:01<00:05, 276MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  19% 377M/1.95G [00:01<00:05, 313MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  22% 419M/1.95G [00:01<00:04, 323MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  24% 461M/1.95G [00:01<00:04, 328MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  26% 503M/1.95G [00:01<00:04, 344MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  28% 545M/1.95G [00:01<00:04, 328MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  30% 587M/1.95G [00:02<00:04, 318MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  32% 629M/1.95G [00:02<00:04, 293MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  34% 661M/1.95G [00:02<00:04, 291MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  36% 703M/1.95G [00:02<00:03, 319MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  38% 744M/1.95G [00:02<00:03, 302MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  40% 786M/1.95G [00:02<00:03, 302MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  42% 818M/1.95G [00:02<00:04, 274MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  44% 849M/1.95G [00:03<00:04, 268MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  45% 881M/1.95G [00:03<00:04, 257MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  47% 912M/1.95G [00:03<00:04, 221MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  49% 954M/1.95G [00:03<00:03, 250MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  51% 996M/1.95G [00:03<00:03, 271MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  53% 1.04G/1.95G [00:03<00:03, 290MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  56% 1.09G/1.95G [00:03<00:02, 327MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  58% 1.13G/1.95G [00:03<00:02, 335MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  60% 1.17G/1.95G [00:04<00:02, 312MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  62% 1.22G/1.95G [00:04<00:02, 323MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  65% 1.26G/1.95G [00:04<00:02, 309MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  67% 1.30G/1.95G [00:04<00:01, 334MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  69% 1.34G/1.95G [00:04<00:01, 341MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  71% 1.38G/1.95G [00:04<00:01, 355MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  74% 1.44G/1.95G [00:04<00:01, 379MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  76% 1.48G/1.95G [00:04<00:01, 368MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  78% 1.52G/1.95G [00:05<00:01, 367MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  81% 1.57G/1.95G [00:05<00:00, 398MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  83% 1.61G/1.95G [00:05<00:00, 399MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  85% 1.66G/1.95G [00:05<00:00, 374MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  87% 1.70G/1.95G [00:05<00:00, 372MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  89% 1.74G/1.95G [00:05<00:00, 373MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  91% 1.78G/1.95G [00:05<00:00, 330MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  94% 1.84G/1.95G [00:05<00:00, 358MB/s]\u001b[A\n","model-00001-of-00008.safetensors:  96% 1.88G/1.95G [00:06<00:00, 343MB/s]\u001b[A\n","model-00001-of-00008.safetensors: 100% 1.95G/1.95G [00:06<00:00, 311MB/s]\n","Downloading shards:  12% 1/8 [00:06<00:47,  6.80s/it]\n","model-00002-of-00008.safetensors:   0% 0.00/1.95G [00:00<?, ?B/s]\u001b[A\n","model-00002-of-00008.safetensors:   3% 52.4M/1.95G [00:00<00:04, 449MB/s]\u001b[A\n","model-00002-of-00008.safetensors:   5% 105M/1.95G [00:00<00:04, 459MB/s] \u001b[A\n","model-00002-of-00008.safetensors:   8% 157M/1.95G [00:00<00:03, 451MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  11% 210M/1.95G [00:00<00:03, 455MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  13% 262M/1.95G [00:00<00:03, 445MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  16% 315M/1.95G [00:00<00:03, 448MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  19% 367M/1.95G [00:00<00:03, 447MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  22% 419M/1.95G [00:00<00:03, 440MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  24% 472M/1.95G [00:01<00:03, 433MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  27% 524M/1.95G [00:01<00:03, 422MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  30% 577M/1.95G [00:01<00:03, 431MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  32% 629M/1.95G [00:01<00:03, 432MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  35% 682M/1.95G [00:01<00:02, 438MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  38% 734M/1.95G [00:01<00:02, 436MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  40% 786M/1.95G [00:01<00:02, 439MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  43% 839M/1.95G [00:01<00:02, 434MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  46% 891M/1.95G [00:02<00:02, 443MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  48% 944M/1.95G [00:02<00:02, 442MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  51% 996M/1.95G [00:02<00:02, 445MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  54% 1.05G/1.95G [00:02<00:01, 449MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  57% 1.10G/1.95G [00:02<00:01, 458MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  59% 1.15G/1.95G [00:02<00:01, 460MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  62% 1.21G/1.95G [00:02<00:01, 468MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  65% 1.26G/1.95G [00:02<00:01, 473MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  67% 1.31G/1.95G [00:02<00:01, 473MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  70% 1.36G/1.95G [00:03<00:01, 462MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  73% 1.42G/1.95G [00:03<00:01, 454MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  75% 1.47G/1.95G [00:03<00:01, 457MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  78% 1.52G/1.95G [00:03<00:00, 461MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  81% 1.57G/1.95G [00:03<00:01, 303MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  84% 1.63G/1.95G [00:03<00:00, 342MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  86% 1.68G/1.95G [00:03<00:00, 364MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  88% 1.72G/1.95G [00:04<00:00, 373MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  91% 1.77G/1.95G [00:04<00:00, 389MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  94% 1.82G/1.95G [00:04<00:00, 398MB/s]\u001b[A\n","model-00002-of-00008.safetensors:  96% 1.88G/1.95G [00:04<00:00, 415MB/s]\u001b[A\n","model-00002-of-00008.safetensors: 100% 1.95G/1.95G [00:07<00:00, 251MB/s] \n","Downloading shards:  25% 2/8 [00:15<00:46,  7.70s/it]\n","model-00003-of-00008.safetensors:   0% 0.00/1.98G [00:00<?, ?B/s]\u001b[A\n","model-00003-of-00008.safetensors:   3% 52.4M/1.98G [00:00<00:03, 486MB/s]\u001b[A\n","model-00003-of-00008.safetensors:   5% 105M/1.98G [00:00<00:03, 507MB/s] \u001b[A\n","model-00003-of-00008.safetensors:   8% 157M/1.98G [00:00<00:03, 511MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  11% 210M/1.98G [00:00<00:03, 508MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  13% 262M/1.98G [00:00<00:03, 502MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  16% 315M/1.98G [00:00<00:03, 495MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  19% 367M/1.98G [00:00<00:03, 477MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  21% 419M/1.98G [00:00<00:03, 482MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  24% 472M/1.98G [00:00<00:03, 486MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  27% 535M/1.98G [00:01<00:02, 511MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  30% 598M/1.98G [00:01<00:02, 526MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  33% 661M/1.98G [00:01<00:02, 533MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  37% 724M/1.98G [00:01<00:02, 515MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  39% 776M/1.98G [00:01<00:02, 506MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  42% 828M/1.98G [00:01<00:02, 497MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  44% 881M/1.98G [00:01<00:02, 481MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  47% 933M/1.98G [00:01<00:02, 479MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  50% 986M/1.98G [00:01<00:02, 480MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  52% 1.04G/1.98G [00:02<00:01, 487MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  55% 1.09G/1.98G [00:02<00:01, 495MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  58% 1.14G/1.98G [00:02<00:01, 494MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  60% 1.20G/1.98G [00:02<00:01, 487MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  63% 1.25G/1.98G [00:02<00:01, 486MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  66% 1.30G/1.98G [00:02<00:01, 486MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  68% 1.35G/1.98G [00:02<00:01, 489MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  71% 1.41G/1.98G [00:02<00:01, 495MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  74% 1.46G/1.98G [00:02<00:01, 492MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  76% 1.51G/1.98G [00:03<00:01, 338MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  78% 1.55G/1.98G [00:03<00:01, 271MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  81% 1.60G/1.98G [00:03<00:01, 313MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  84% 1.66G/1.98G [00:03<00:00, 349MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  86% 1.71G/1.98G [00:03<00:00, 370MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  89% 1.76G/1.98G [00:03<00:00, 374MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  91% 1.80G/1.98G [00:04<00:00, 336MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  93% 1.85G/1.98G [00:04<00:00, 350MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  95% 1.89G/1.98G [00:04<00:00, 332MB/s]\u001b[A\n","model-00003-of-00008.safetensors:  97% 1.93G/1.98G [00:04<00:00, 343MB/s]\u001b[A\n","model-00003-of-00008.safetensors: 100% 1.98G/1.98G [00:04<00:00, 420MB/s]\n","Downloading shards:  38% 3/8 [00:20<00:32,  6.57s/it]\n","model-00004-of-00008.safetensors:   0% 0.00/1.95G [00:00<?, ?B/s]\u001b[A\n","model-00004-of-00008.safetensors:   2% 31.5M/1.95G [00:00<00:06, 296MB/s]\u001b[A\n","model-00004-of-00008.safetensors:   4% 73.4M/1.95G [00:00<00:05, 335MB/s]\u001b[A\n","model-00004-of-00008.safetensors:   6% 115M/1.95G [00:00<00:05, 336MB/s] \u001b[A\n","model-00004-of-00008.safetensors:   8% 157M/1.95G [00:00<00:05, 313MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  10% 199M/1.95G [00:00<00:05, 326MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  12% 241M/1.95G [00:00<00:05, 333MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  15% 283M/1.95G [00:00<00:05, 299MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  17% 325M/1.95G [00:01<00:05, 304MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  18% 357M/1.95G [00:01<00:05, 284MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  20% 398M/1.95G [00:01<00:05, 296MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  22% 430M/1.95G [00:01<00:05, 300MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  24% 472M/1.95G [00:01<00:04, 306MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  26% 503M/1.95G [00:01<00:04, 293MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  27% 535M/1.95G [00:01<00:05, 273MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  29% 566M/1.95G [00:01<00:05, 275MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  31% 608M/1.95G [00:02<00:04, 288MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  33% 640M/1.95G [00:02<00:04, 290MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  34% 671M/1.95G [00:02<00:04, 296MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  37% 713M/1.95G [00:02<00:03, 311MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  39% 755M/1.95G [00:02<00:03, 332MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  41% 797M/1.95G [00:02<00:03, 315MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  43% 839M/1.95G [00:02<00:03, 301MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  45% 870M/1.95G [00:02<00:03, 302MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  47% 912M/1.95G [00:03<00:03, 308MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  49% 954M/1.95G [00:03<00:03, 324MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  51% 996M/1.95G [00:03<00:03, 310MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  53% 1.04G/1.95G [00:03<00:02, 309MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  55% 1.08G/1.95G [00:03<00:02, 318MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  58% 1.12G/1.95G [00:03<00:02, 308MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  59% 1.15G/1.95G [00:03<00:03, 241MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  61% 1.18G/1.95G [00:04<00:03, 222MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  62% 1.22G/1.95G [00:04<00:03, 214MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  65% 1.26G/1.95G [00:04<00:02, 243MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  67% 1.30G/1.95G [00:04<00:02, 260MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  68% 1.33G/1.95G [00:04<00:02, 268MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  70% 1.36G/1.95G [00:04<00:02, 264MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  72% 1.39G/1.95G [00:04<00:02, 247MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  74% 1.44G/1.95G [00:04<00:01, 273MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  76% 1.48G/1.95G [00:05<00:01, 292MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  78% 1.52G/1.95G [00:05<00:01, 312MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  80% 1.56G/1.95G [00:05<00:01, 323MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  82% 1.60G/1.95G [00:05<00:01, 327MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  85% 1.65G/1.95G [00:05<00:00, 343MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  87% 1.69G/1.95G [00:05<00:00, 354MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  89% 1.73G/1.95G [00:05<00:00, 336MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  91% 1.77G/1.95G [00:05<00:00, 322MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  93% 1.81G/1.95G [00:06<00:00, 330MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  96% 1.87G/1.95G [00:06<00:00, 349MB/s]\u001b[A\n","model-00004-of-00008.safetensors:  98% 1.91G/1.95G [00:06<00:00, 339MB/s]\u001b[A\n","model-00004-of-00008.safetensors: 100% 1.95G/1.95G [00:06<00:00, 299MB/s]\n","Downloading shards:  50% 4/8 [00:27<00:27,  6.76s/it]\n","model-00005-of-00008.safetensors:   0% 0.00/1.98G [00:00<?, ?B/s]\u001b[A\n","model-00005-of-00008.safetensors:   2% 31.5M/1.98G [00:00<00:06, 287MB/s]\u001b[A\n","model-00005-of-00008.safetensors:   3% 62.9M/1.98G [00:00<00:07, 242MB/s]\u001b[A\n","model-00005-of-00008.safetensors:   5% 94.4M/1.98G [00:00<00:07, 253MB/s]\u001b[A\n","model-00005-of-00008.safetensors:   6% 126M/1.98G [00:00<00:06, 269MB/s] \u001b[A\n","model-00005-of-00008.safetensors:   8% 168M/1.98G [00:00<00:05, 304MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  11% 210M/1.98G [00:00<00:05, 313MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  12% 241M/1.98G [00:00<00:05, 291MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  14% 283M/1.98G [00:00<00:05, 307MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  16% 325M/1.98G [00:01<00:05, 321MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  19% 367M/1.98G [00:01<00:04, 343MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  21% 409M/1.98G [00:01<00:04, 348MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  23% 451M/1.98G [00:01<00:04, 310MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  25% 493M/1.98G [00:01<00:04, 324MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  27% 535M/1.98G [00:01<00:04, 333MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  29% 577M/1.98G [00:01<00:04, 327MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  31% 619M/1.98G [00:02<00:05, 263MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  33% 661M/1.98G [00:02<00:04, 283MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  35% 692M/1.98G [00:02<00:04, 283MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  37% 734M/1.98G [00:02<00:04, 301MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  39% 765M/1.98G [00:02<00:04, 304MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  40% 797M/1.98G [00:02<00:03, 304MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  42% 828M/1.98G [00:02<00:03, 295MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  44% 881M/1.98G [00:02<00:03, 343MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  47% 923M/1.98G [00:02<00:03, 347MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  49% 965M/1.98G [00:03<00:02, 350MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  51% 1.02G/1.98G [00:03<00:02, 386MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  54% 1.07G/1.98G [00:03<00:02, 400MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  56% 1.11G/1.98G [00:03<00:02, 386MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  58% 1.15G/1.98G [00:03<00:02, 386MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  60% 1.20G/1.98G [00:03<00:02, 391MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  62% 1.24G/1.98G [00:03<00:01, 380MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  65% 1.29G/1.98G [00:03<00:01, 403MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  67% 1.33G/1.98G [00:03<00:01, 405MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  69% 1.37G/1.98G [00:04<00:01, 394MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  72% 1.42G/1.98G [00:04<00:01, 394MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  74% 1.46G/1.98G [00:04<00:01, 396MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  76% 1.51G/1.98G [00:04<00:01, 411MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  78% 1.55G/1.98G [00:04<00:01, 386MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  81% 1.59G/1.98G [00:04<00:01, 385MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  83% 1.64G/1.98G [00:04<00:00, 393MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  85% 1.68G/1.98G [00:04<00:00, 392MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  87% 1.72G/1.98G [00:05<00:00, 380MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  89% 1.76G/1.98G [00:05<00:00, 336MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  91% 1.80G/1.98G [00:05<00:00, 357MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  93% 1.85G/1.98G [00:05<00:00, 342MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  95% 1.89G/1.98G [00:05<00:00, 298MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  97% 1.92G/1.98G [00:05<00:00, 274MB/s]\u001b[A\n","model-00005-of-00008.safetensors:  99% 1.95G/1.98G [00:05<00:00, 257MB/s]\u001b[A\n","model-00005-of-00008.safetensors: 100% 1.98G/1.98G [00:06<00:00, 330MB/s]\n","Downloading shards:  62% 5/8 [00:33<00:20,  6.68s/it]\n","model-00006-of-00008.safetensors:   0% 0.00/1.95G [00:00<?, ?B/s]\u001b[A\n","model-00006-of-00008.safetensors:   3% 52.4M/1.95G [00:00<00:04, 452MB/s]\u001b[A\n","model-00006-of-00008.safetensors:   5% 105M/1.95G [00:00<00:04, 455MB/s] \u001b[A\n","model-00006-of-00008.safetensors:   8% 157M/1.95G [00:06<01:32, 19.4MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  11% 220M/1.95G [00:06<00:51, 33.7MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  15% 283M/1.95G [00:06<00:31, 52.9MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  18% 346M/1.95G [00:06<00:20, 78.0MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  21% 409M/1.95G [00:06<00:14, 110MB/s] \u001b[A\n","model-00006-of-00008.safetensors:  24% 472M/1.95G [00:06<00:09, 148MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  27% 535M/1.95G [00:06<00:08, 162MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  30% 587M/1.95G [00:06<00:06, 199MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  33% 640M/1.95G [00:07<00:05, 239MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  36% 692M/1.95G [00:07<00:04, 279MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  38% 744M/1.95G [00:07<00:03, 322MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  41% 797M/1.95G [00:07<00:03, 361MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  44% 849M/1.95G [00:07<00:02, 395MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  46% 902M/1.95G [00:07<00:02, 422MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  49% 954M/1.95G [00:07<00:02, 443MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  52% 1.01G/1.95G [00:07<00:02, 430MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  54% 1.06G/1.95G [00:07<00:01, 452MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  57% 1.11G/1.95G [00:08<00:02, 403MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  60% 1.16G/1.95G [00:08<00:02, 325MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  62% 1.21G/1.95G [00:08<00:02, 340MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  65% 1.26G/1.95G [00:08<00:01, 380MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  67% 1.30G/1.95G [00:08<00:01, 375MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  69% 1.34G/1.95G [00:08<00:01, 364MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  71% 1.38G/1.95G [00:08<00:01, 319MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  73% 1.43G/1.95G [00:09<00:01, 271MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  76% 1.48G/1.95G [00:09<00:01, 321MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  78% 1.52G/1.95G [00:09<00:01, 323MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  80% 1.56G/1.95G [00:09<00:01, 320MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  82% 1.60G/1.95G [00:09<00:01, 189MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  84% 1.64G/1.95G [00:10<00:01, 191MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  87% 1.70G/1.95G [00:10<00:00, 257MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  90% 1.75G/1.95G [00:10<00:00, 302MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  93% 1.80G/1.95G [00:10<00:00, 337MB/s]\u001b[A\n","model-00006-of-00008.safetensors:  95% 1.86G/1.95G [00:10<00:00, 378MB/s]\u001b[A\n","model-00006-of-00008.safetensors: 100% 1.95G/1.95G [00:11<00:00, 174MB/s]\n","Downloading shards:  75% 6/8 [00:45<00:16,  8.40s/it]\n","model-00007-of-00008.safetensors:   0% 0.00/1.98G [00:00<?, ?B/s]\u001b[A\n","model-00007-of-00008.safetensors:   2% 31.5M/1.98G [00:00<00:06, 285MB/s]\u001b[A\n","model-00007-of-00008.safetensors:   3% 62.9M/1.98G [00:00<00:06, 299MB/s]\u001b[A\n","model-00007-of-00008.safetensors:   5% 94.4M/1.98G [00:00<00:06, 298MB/s]\u001b[A\n","model-00007-of-00008.safetensors:   6% 126M/1.98G [00:00<00:06, 302MB/s] \u001b[A\n","model-00007-of-00008.safetensors:   8% 157M/1.98G [00:00<00:06, 301MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  10% 199M/1.98G [00:00<00:05, 319MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  12% 241M/1.98G [00:00<00:05, 291MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  14% 273M/1.98G [00:00<00:06, 254MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  15% 304M/1.98G [00:01<00:06, 263MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  17% 336M/1.98G [00:01<00:06, 250MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  19% 367M/1.98G [00:01<00:07, 227MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  20% 398M/1.98G [00:01<00:06, 229MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  22% 430M/1.98G [00:01<00:07, 206MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  23% 461M/1.98G [00:01<00:06, 218MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  25% 493M/1.98G [00:02<00:09, 163MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  26% 514M/1.98G [00:02<00:09, 158MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  28% 545M/1.98G [00:02<00:08, 178MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  29% 566M/1.98G [00:02<00:07, 180MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  30% 587M/1.98G [00:02<00:08, 167MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  31% 608M/1.98G [00:02<00:07, 172MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  32% 640M/1.98G [00:02<00:06, 199MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  34% 671M/1.98G [00:03<00:06, 196MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  35% 703M/1.98G [00:03<00:06, 193MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  37% 734M/1.98G [00:03<00:06, 196MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  39% 765M/1.98G [00:03<00:05, 220MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  40% 797M/1.98G [00:03<00:04, 237MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  42% 828M/1.98G [00:03<00:05, 219MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  43% 860M/1.98G [00:03<00:04, 230MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  45% 891M/1.98G [00:04<00:05, 204MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  47% 923M/1.98G [00:04<00:06, 158MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  48% 944M/1.98G [00:04<00:09, 105MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  49% 965M/1.98G [00:05<00:10, 99.0MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  50% 986M/1.98G [00:05<00:09, 100MB/s] \u001b[A\n","model-00007-of-00008.safetensors:  51% 1.01G/1.98G [00:05<00:08, 112MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  52% 1.03G/1.98G [00:05<00:09, 101MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  53% 1.05G/1.98G [00:05<00:09, 94.9MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  54% 1.07G/1.98G [00:06<00:08, 108MB/s] \u001b[A\n","model-00007-of-00008.safetensors:  55% 1.09G/1.98G [00:06<00:07, 119MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  56% 1.11G/1.98G [00:06<00:06, 126MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  57% 1.13G/1.98G [00:06<00:06, 139MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  59% 1.16G/1.98G [00:06<00:04, 168MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  60% 1.18G/1.98G [00:06<00:05, 139MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  61% 1.21G/1.98G [00:06<00:05, 129MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  62% 1.24G/1.98G [00:07<00:05, 136MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  64% 1.26G/1.98G [00:07<00:06, 110MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  65% 1.28G/1.98G [00:07<00:06, 117MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  66% 1.30G/1.98G [00:07<00:05, 130MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  67% 1.33G/1.98G [00:07<00:04, 153MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  69% 1.36G/1.98G [00:08<00:03, 178MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  70% 1.39G/1.98G [00:08<00:03, 174MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  72% 1.42G/1.98G [00:08<00:04, 123MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  73% 1.44G/1.98G [00:08<00:04, 112MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  74% 1.46G/1.98G [00:08<00:04, 111MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  75% 1.48G/1.98G [00:09<00:04, 116MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  76% 1.51G/1.98G [00:09<00:03, 145MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  77% 1.53G/1.98G [00:09<00:03, 144MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  78% 1.55G/1.98G [00:09<00:02, 147MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  79% 1.57G/1.98G [00:09<00:02, 143MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  81% 1.59G/1.98G [00:09<00:02, 145MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  82% 1.61G/1.98G [00:09<00:02, 146MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  83% 1.64G/1.98G [00:10<00:02, 131MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  84% 1.66G/1.98G [00:10<00:03, 88.0MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  85% 1.68G/1.98G [00:10<00:03, 83.5MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  85% 1.69G/1.98G [00:11<00:04, 65.0MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  86% 1.71G/1.98G [00:11<00:03, 84.0MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  87% 1.73G/1.98G [00:11<00:02, 93.6MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  89% 1.76G/1.98G [00:11<00:01, 119MB/s] \u001b[A\n","model-00007-of-00008.safetensors:  90% 1.78G/1.98G [00:11<00:01, 105MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  92% 1.82G/1.98G [00:12<00:00, 157MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  94% 1.86G/1.98G [00:12<00:00, 139MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  95% 1.88G/1.98G [00:12<00:00, 134MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  96% 1.90G/1.98G [00:12<00:00, 143MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  97% 1.92G/1.98G [00:12<00:00, 125MB/s]\u001b[A\n","model-00007-of-00008.safetensors:  98% 1.94G/1.98G [00:12<00:00, 134MB/s]\u001b[A\n","model-00007-of-00008.safetensors: 100% 1.98G/1.98G [00:13<00:00, 150MB/s]\n","Downloading shards:  88% 7/8 [00:59<00:10, 10.16s/it]\n","model-00008-of-00008.safetensors:   0% 0.00/1.75G [00:00<?, ?B/s]\u001b[A\n","model-00008-of-00008.safetensors:   3% 52.4M/1.75G [00:00<00:03, 435MB/s]\u001b[A\n","model-00008-of-00008.safetensors:   6% 105M/1.75G [00:00<00:03, 439MB/s] \u001b[A\n","model-00008-of-00008.safetensors:   9% 157M/1.75G [00:00<00:03, 439MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  12% 210M/1.75G [00:00<00:03, 437MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  15% 262M/1.75G [00:00<00:03, 432MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  18% 315M/1.75G [00:00<00:03, 439MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  21% 367M/1.75G [00:00<00:03, 425MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  24% 419M/1.75G [00:00<00:03, 421MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  27% 472M/1.75G [00:01<00:02, 432MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  30% 524M/1.75G [00:01<00:02, 437MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  33% 577M/1.75G [00:01<00:02, 445MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  36% 629M/1.75G [00:01<00:02, 452MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  39% 682M/1.75G [00:01<00:02, 456MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  42% 734M/1.75G [00:01<00:02, 459MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  45% 786M/1.75G [00:01<00:02, 471MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  48% 839M/1.75G [00:01<00:01, 480MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  51% 891M/1.75G [00:01<00:01, 484MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  54% 944M/1.75G [00:02<00:01, 470MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  57% 996M/1.75G [00:02<00:02, 372MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  59% 1.04G/1.75G [00:02<00:02, 311MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  62% 1.08G/1.75G [00:02<00:02, 288MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  64% 1.12G/1.75G [00:02<00:02, 275MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  66% 1.15G/1.75G [00:02<00:02, 266MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  68% 1.18G/1.75G [00:03<00:02, 252MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  70% 1.22G/1.75G [00:03<00:02, 243MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  71% 1.25G/1.75G [00:03<00:02, 234MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  73% 1.28G/1.75G [00:03<00:02, 225MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  75% 1.31G/1.75G [00:03<00:02, 215MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  77% 1.34G/1.75G [00:04<00:04, 82.4MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  80% 1.39G/1.75G [00:04<00:02, 124MB/s] \u001b[A\n","model-00008-of-00008.safetensors:  83% 1.45G/1.75G [00:04<00:01, 170MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  86% 1.50G/1.75G [00:05<00:01, 217MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  89% 1.55G/1.75G [00:05<00:00, 264MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  92% 1.60G/1.75G [00:05<00:00, 305MB/s]\u001b[A\n","model-00008-of-00008.safetensors:  95% 1.66G/1.75G [00:05<00:00, 343MB/s]\u001b[A\n","model-00008-of-00008.safetensors: 100% 1.75G/1.75G [00:05<00:00, 314MB/s]\n","Downloading shards: 100% 8/8 [01:05<00:00,  8.19s/it]\n","[INFO|modeling_utils.py:1519] 2024-07-11 15:28:57,306 >> Instantiating InternLM2ForCausalLM model under default dtype torch.bfloat16.\n","[INFO|configuration_utils.py:962] 2024-07-11 15:28:57,307 >> Generate config GenerationConfig {\n","  \"bos_token_id\": 1,\n","  \"eos_token_id\": 2,\n","  \"pad_token_id\": 2\n","}\n","\n","Loading checkpoint shards: 100% 8/8 [00:07<00:00,  1.12it/s]\n","[INFO|modeling_utils.py:4280] 2024-07-11 15:29:04,587 >> All model checkpoint weights were used when initializing InternLM2ForCausalLM.\n","\n","[INFO|modeling_utils.py:4288] 2024-07-11 15:29:04,587 >> All the weights of InternLM2ForCausalLM were initialized from the model checkpoint at internlm/internlm2_5-7b-chat-1m.\n","If your task is similar to the task the model of the checkpoint was trained on, you can already use InternLM2ForCausalLM for predictions without further training.\n","generation_config.json: 100% 123/123 [00:00<00:00, 902kB/s]\n","[INFO|configuration_utils.py:917] 2024-07-11 15:29:05,100 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--internlm--internlm2_5-7b-chat-1m/snapshots/8d1a709a04d71440ef3df6ebbe204672f411c8b6/generation_config.json\n","[INFO|configuration_utils.py:962] 2024-07-11 15:29:05,101 >> Generate config GenerationConfig {\n","  \"bos_token_id\": 1,\n","  \"eos_token_id\": [\n","    2,\n","    92542\n","  ],\n","  \"pad_token_id\": 2\n","}\n","\n","07/11/2024 15:29:05 - INFO - llamafactory.model.model_utils.checkpointing - Upcasting layernorm weights in float32.\n","07/11/2024 15:29:05 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.\n","07/11/2024 15:29:05 - INFO - llamafactory.model.model_utils.attention - Using vanilla attention implementation.\n","07/11/2024 15:29:05 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.\n","07/11/2024 15:29:05 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA\n","07/11/2024 15:29:05 - INFO - llamafactory.model.model_utils.misc - Found linear modules: wo,w3,wqkv,w2,w1\n","07/11/2024 15:29:05 - INFO - llamafactory.model.loader - trainable params: 18,874,368 || all params: 7,756,582,912 || trainable%: 0.2433\n","[INFO|trainer.py:641] 2024-07-11 15:29:05,979 >> Using auto half precision backend\n","07/11/2024 15:29:07 - INFO - llamafactory.train.trainer_utils - Using LoRA+ optimizer with loraplus lr ratio 16.00.\n","[INFO|trainer.py:2078] 2024-07-11 15:29:07,222 >> ***** Running training *****\n","[INFO|trainer.py:2079] 2024-07-11 15:29:07,222 >>   Num examples = 4,500\n","[INFO|trainer.py:2080] 2024-07-11 15:29:07,222 >>   Num Epochs = 4\n","[INFO|trainer.py:2081] 2024-07-11 15:29:07,222 >>   Instantaneous batch size per device = 1\n","[INFO|trainer.py:2084] 2024-07-11 15:29:07,222 >>   Total train batch size (w. parallel, distributed & accumulation) = 8\n","[INFO|trainer.py:2085] 2024-07-11 15:29:07,222 >>   Gradient Accumulation steps = 8\n","[INFO|trainer.py:2086] 2024-07-11 15:29:07,222 >>   Total optimization steps = 2,248\n","[INFO|trainer.py:2087] 2024-07-11 15:29:07,226 >>   Number of trainable parameters = 18,874,368\n","[INFO|integration_utils.py:723] 2024-07-11 15:29:07,230 >> Automatic Weights & Biases logging enabled, to disable set os.environ[\"WANDB_DISABLED\"] = \"true\"\n","\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33minflaton-sg\u001b[0m (\u001b[33minflaton-ai\u001b[0m). Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n","\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.17.4\n","\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m/content/drive/MyDrive/logical-reasoning/llama-factory/wandb/run-20240711_152908-qhb0out3\u001b[0m\n","\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\n","\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33minternlm2_5_7b\u001b[0m\n","\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/inflaton-ai/huggingface\u001b[0m\n","\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/inflaton-ai/huggingface/runs/qhb0out3\u001b[0m\n","{'loss': 0.4683, 'grad_norm': 3.4465599060058594, 'learning_rate': 4.4444444444444447e-05, 'epoch': 0.18}\n","  8% 174/2248 [17:06<3:24:19,  5.91s/it]"]}],"source":["%%time\n","\n","!sh ./scripts/tune-lf.sh config/internlm2_5_7b_lora_sft_bf16_p2.yaml"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"L370pvGTZBrN"},"outputs":[],"source":["def evaluate_model_all_epochs(model_name, adapter_path_base, num_train_epochs, start_epoch=0, load_in_4bit=True, num_of_entries=-1):\n","    os.environ[\"MODEL_NAME\"] = model_name\n","    os.environ[\"LOAD_IN_4BIT\"] = \"true\" if load_in_4bit else \"false\"\n","    for i in range(start_epoch, num_train_epochs + 1):\n","        print(f\"Epoch {i}\")\n","        if i == 0:\n","            os.unsetenv(\"ADAPTER_NAME_OR_PATH\")\n","        else:\n","            adapter_path = f\"{adapter_path_base}/checkpoint-{562 * i}\"\n","            os.environ[\"ADAPTER_NAME_OR_PATH\"] = adapter_path\n","\n","        !python llm_toolkit/eval_logical_reasoning.py {num_of_entries}"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"WUFjhxmiZBrN"},"outputs":[],"source":["%%time\n","\n","evaluate_model_all_epochs(\"internlm/internlm2_5-7b-chat-1m\", \"llama-factory/saves/internlm2_5_7b/lora/sft_bf16_p2\", 4, start_epoch=0, load_in_4bit=False, num_of_entries=-1)"]}],"metadata":{"accelerator":"GPU","application/vnd.databricks.v1+notebook":{"dashboards":[],"environmentMetadata":null,"language":"python","notebookMetadata":{"mostRecentlyExecutedCommandWithImplicitDF":{"commandId":-1,"dataframes":["_sqldf"]},"pythonIndentUnit":4},"notebookName":"10_eval-lf-medium-py3.11","widgets":{}},"colab":{"gpuType":"L4","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}