eval glm-4 base model

competition/10c_InternLM_M3_eval.ipynb

@@ -0,0 +1 @@
+{"cells":[{"cell_type":"code","execution_count":1,"metadata":{"executionInfo":{"elapsed":476,"status":"ok","timestamp":1720679526275,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"uWKRSV6eZsCn"},"outputs":[],"source":["%load_ext autoreload\n","%autoreload 2"]},{"cell_type":"code","execution_count":2,"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/"},"executionInfo":{"elapsed":2534,"status":"ok","timestamp":1720679529344,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"xwFh14uiZBrI","outputId":"d767799c-34c2-46a5-f052-378146a55321"},"outputs":[],"source":["from pathlib import Path\n","\n","try:\n","    from google.colab import drive\n","\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":{"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/"},"executionInfo":{"elapsed":5,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"G5pNu3zgZBrL","outputId":"160a554f-fb08-4aa0-bc00-0422fb7c1fac"},"outputs":[{"name":"stdout","output_type":"stream","text":["workding dir: /Users/inflaton/code/engd/projects/logical-reasoning\n"]}],"source":["import os\n","import sys\n","from pathlib import Path\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":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"ac667aba-076e-4de6-9984-8f6a67cb09cd","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":4,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"0dVRAabNZBrL","outputId":"b977e116-df16-47cd-9160-a24f611da687"},"outputs":[{"data":{"text/plain":["False"]},"execution_count":4,"metadata":{},"output_type":"execute_result"}],"source":["need_to_setup_env = False\n","need_to_setup_env"]},{"cell_type":"code","execution_count":5,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"72f9cf79-7b0d-4d9e-90a0-1fa5251b947f","showTitle":false,"title":""},"executionInfo":{"elapsed":4,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"hKUOfP2HZBrL"},"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]\n","    \n","    os.chdir(workding_dir)\n","    sys.path.append(workding_dir)\n","    print(\"workding dir:\", workding_dir)"]},{"cell_type":"code","execution_count":6,"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/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"hPCC-6m7ZBrM","outputId":"c7aa2c96-5e99-440a-c148-201d79465ff9"},"outputs":[{"name":"stdout","output_type":"stream","text":["loading env vars from: /Users/inflaton/code/engd/projects/logical-reasoning/.env\n"]},{"data":{"text/plain":["True"]},"execution_count":6,"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":7,"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/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"1M3IraVtZBrM","outputId":"29ab35f6-2970-4ade-d85d-3174acf8cda0"},"outputs":[{"name":"stdout","output_type":"stream","text":["internlm/internlm2_5-7b-chat-1m llama-factory/saves/internlm2_5_7b/lora/sft_bf16_p2_full/checkpoint-88 False datasets/mgtv results/mgtv-results_m3.csv\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)"]},{"cell_type":"code","execution_count":8,"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/"},"executionInfo":{"elapsed":564,"status":"ok","timestamp":1720679529907,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"UgMvt6dIZBrM","outputId":"ce37581c-fd26-46c2-ad87-d933d99f68f7"},"outputs":[{"name":"stdout","output_type":"stream","text":["Python 3.11.9\n","\u001b[33mWARNING: Package(s) not found: flash-attn\u001b[0m\u001b[33m\n","\u001b[0mCPU times: user 3.96 ms, sys: 7.26 ms, total: 11.2 ms\n","Wall time: 643 ms\n"]}],"source":["%%time\n","!python --version\n","!pip show flash-attn"]},{"cell_type":"code","execution_count":9,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":1685,"status":"ok","timestamp":1720679531591,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"ZuS_FsLyZBrN","outputId":"2cba0105-c505-4395-afbd-2f2fee6581d0"},"outputs":[{"name":"stdout","output_type":"stream","text":["loading /Users/inflaton/code/engd/projects/logical-reasoning/llm_toolkit/logical_reasoning_utils.py\n","MPS is available\n"]}],"source":["from llm_toolkit.llm_utils import *\n","from llm_toolkit.logical_reasoning_utils import *\n","\n","device = check_gpu()"]},{"cell_type":"code","execution_count":10,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["loading model: internlm/internlm2_5-7b-chat-1m with adapter: llama-factory/saves/internlm2_5_7b/lora/sft_bf16_p2_full/checkpoint-88\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"74891a59a88c4845845a61327a619b22","version_major":2,"version_minor":0},"text/plain":["Loading checkpoint shards:   0%|          | 0/8 [00:00<?, ?it/s]"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["CPU times: user 2.44 s, sys: 4.12 s, total: 6.56 s\n","Wall time: 7.18 s\n"]}],"source":["%%time\n","\n","model, tokenizer = load_model(model_name, adapter_name_or_path=adapter_name_or_path, using_llama_factory=False)"]},{"cell_type":"code","execution_count":11,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["loading train/test data files\n","DatasetDict({\n","    train: Dataset({\n","        features: ['text', 'label', 'answer', 'title', 'puzzle', 'truth', 'train_text', 'prompt'],\n","        num_rows: 25000\n","    })\n","    test: Dataset({\n","        features: ['text', 'label', 'answer', 'title', 'puzzle', 'truth', 'train_text', 'prompt'],\n","        num_rows: 3000\n","    })\n","})\n"]}],"source":["datasets = load_logical_reasoning_dataset(\n","    data_path,\n","    tokenizer=tokenizer,\n","    chinese_prompt=not use_english_datasets,\n","    using_p1=False,\n",")"]},{"cell_type":"code","execution_count":12,"metadata":{},"outputs":[],"source":["def evaluate_model(model, tokenizer, model_name, dataset):\n","    print(f\"Evaluating model: {model_name} on {device}\")\n","    predictions = eval_model(model, tokenizer, dataset, device=device)\n","\n","    save_results(\n","        model_name,\n","        results_path,\n","        dataset,\n","        predictions,\n","        debug=False,\n","    )\n","\n","    metrics = calc_metrics(dataset[\"label\"], predictions, debug=False)\n","    print(metrics)"]},{"cell_type":"code","execution_count":13,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["Evaluating model: internlm/internlm2_5-7b-chat-1m_llama-factory/saves/internlm2_5_7b/lora/sft_bf16_p2_full/checkpoint-88 on mps\n"]},{"name":"stderr","output_type":"stream","text":["  0%|          | 1/3000 [00:03<2:33:23,  3.07s/it]"]},{"name":"stdout","output_type":"stream","text":["--------\n","step 1: 不是</s>\n","--------\n","step 2: 不是\n","--------\n","step 3: 不是\n","--------\n","step 4: 不是\n","--------\n","step 5: 不是\n"]},{"name":"stderr","output_type":"stream","text":[" 57%|█████▋    | 1709/3000 [7:39:10<1:11:42,  3.33s/it]   "]}],"source":["%%time\n","\n","evaluate_model(model, tokenizer, f\"{model_name}_{adapter_name_or_path}\", datasets[\"test\"])"]}],"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}

competition/14_GLM-4_M3_eval.ipynb

@@ -0,0 +1 @@
+{"cells":[{"cell_type":"code","execution_count":1,"metadata":{"executionInfo":{"elapsed":476,"status":"ok","timestamp":1720679526275,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"uWKRSV6eZsCn"},"outputs":[],"source":["%load_ext autoreload\n","%autoreload 2"]},{"cell_type":"code","execution_count":2,"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/"},"executionInfo":{"elapsed":2534,"status":"ok","timestamp":1720679529344,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"xwFh14uiZBrI","outputId":"d767799c-34c2-46a5-f052-378146a55321"},"outputs":[],"source":["from pathlib import Path\n","\n","try:\n","    from google.colab import drive\n","\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":{"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/"},"executionInfo":{"elapsed":5,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"G5pNu3zgZBrL","outputId":"160a554f-fb08-4aa0-bc00-0422fb7c1fac"},"outputs":[{"name":"stdout","output_type":"stream","text":["workding dir: /Users/inflaton/code/engd/projects/logical-reasoning\n"]}],"source":["import os\n","import sys\n","from pathlib import Path\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":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"ac667aba-076e-4de6-9984-8f6a67cb09cd","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":4,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"0dVRAabNZBrL","outputId":"b977e116-df16-47cd-9160-a24f611da687"},"outputs":[{"data":{"text/plain":["False"]},"execution_count":4,"metadata":{},"output_type":"execute_result"}],"source":["need_to_setup_env = False\n","need_to_setup_env"]},{"cell_type":"code","execution_count":5,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"72f9cf79-7b0d-4d9e-90a0-1fa5251b947f","showTitle":false,"title":""},"executionInfo":{"elapsed":4,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"hKUOfP2HZBrL"},"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]\n","    \n","    os.chdir(workding_dir)\n","    sys.path.append(workding_dir)\n","    print(\"workding dir:\", workding_dir)"]},{"cell_type":"code","execution_count":6,"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/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"hPCC-6m7ZBrM","outputId":"c7aa2c96-5e99-440a-c148-201d79465ff9"},"outputs":[{"name":"stdout","output_type":"stream","text":["loading env vars from: /Users/inflaton/code/engd/projects/logical-reasoning/.env\n"]},{"data":{"text/plain":["True"]},"execution_count":6,"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":7,"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/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"1M3IraVtZBrM","outputId":"29ab35f6-2970-4ade-d85d-3174acf8cda0"},"outputs":[{"name":"stdout","output_type":"stream","text":["THUDM/glm-4-9b-chat-1m None False datasets/mgtv results/mgtv-results_m3.csv\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)"]},{"cell_type":"code","execution_count":8,"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/"},"executionInfo":{"elapsed":564,"status":"ok","timestamp":1720679529907,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"UgMvt6dIZBrM","outputId":"ce37581c-fd26-46c2-ad87-d933d99f68f7"},"outputs":[{"name":"stdout","output_type":"stream","text":["Python 3.11.9\n","\u001b[33mWARNING: Package(s) not found: flash-attn\u001b[0m\u001b[33m\n","\u001b[0mCPU times: user 4.12 ms, sys: 9.4 ms, total: 13.5 ms\n","Wall time: 651 ms\n"]}],"source":["%%time\n","!python --version\n","!pip show flash-attn"]},{"cell_type":"code","execution_count":9,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":1685,"status":"ok","timestamp":1720679531591,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"ZuS_FsLyZBrN","outputId":"2cba0105-c505-4395-afbd-2f2fee6581d0"},"outputs":[{"name":"stdout","output_type":"stream","text":["loading /Users/inflaton/code/engd/projects/logical-reasoning/llm_toolkit/logical_reasoning_utils.py\n","MPS is available\n"]}],"source":["from llm_toolkit.llm_utils import *\n","from llm_toolkit.logical_reasoning_utils import *\n","\n","device = check_gpu()"]},{"cell_type":"code","execution_count":12,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["loading model: THUDM/glm-4-9b-chat-1m with adapter: None\n"]},{"name":"stderr","output_type":"stream","text":["Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"132c5a39ad11466db54e9cc820789fa1","version_major":2,"version_minor":0},"text/plain":["Downloading shards:   0%|          | 0/10 [00:00<?, ?it/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"a41d42be474b428fa9cb046fa047f52f","version_major":2,"version_minor":0},"text/plain":["model-00002-of-00010.safetensors:  91%|#########1| 1.68G/1.84G [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"73fb4f921cbf4019857647180498a4b9","version_major":2,"version_minor":0},"text/plain":["model-00003-of-00010.safetensors:   0%|          | 0.00/1.99G [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"}],"source":["%%time\n","\n","model, tokenizer = load_model(model_name, adapter_name_or_path=adapter_name_or_path, using_llama_factory=False)"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[{"ename":"NameError","evalue":"name 'tokenizer' is not defined","output_type":"error","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)","Cell \u001b[0;32mIn[11], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m datasets \u001b[38;5;241m=\u001b[39m load_logical_reasoning_dataset(\n\u001b[1;32m      2\u001b[0m     data_path,\n\u001b[0;32m----> 3\u001b[0m     tokenizer\u001b[38;5;241m=\u001b[39m\u001b[43mtokenizer\u001b[49m,\n\u001b[1;32m      4\u001b[0m     chinese_prompt\u001b[38;5;241m=\u001b[39m\u001b[38;5;129;01mnot\u001b[39;00m use_english_datasets,\n\u001b[1;32m      5\u001b[0m     using_p1\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m      6\u001b[0m )\n","\u001b[0;31mNameError\u001b[0m: name 'tokenizer' is not defined"]}],"source":["datasets = load_logical_reasoning_dataset(\n","    data_path,\n","    tokenizer=tokenizer,\n","    chinese_prompt=not use_english_datasets,\n","    using_p1=False,\n",")"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[],"source":["def evaluate_model(model, tokenizer, model_name, dataset):\n","    print(f\"Evaluating model: {model_name} on {device}\")\n","    predictions = eval_model(model, tokenizer, dataset, device=device)\n","\n","    save_results(\n","        model_name,\n","        results_path,\n","        dataset,\n","        predictions,\n","        debug=False,\n","    )\n","\n","    metrics = calc_metrics(dataset[\"label\"], predictions, debug=False)\n","    print(metrics)"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["Evaluating model: internlm/internlm2_5-7b-chat-1m_llama-factory/saves/internlm2_5_7b/lora/sft_bf16_p2_full/checkpoint-88 on mps\n"]},{"name":"stderr","output_type":"stream","text":["  0%|          | 1/3000 [00:06<5:23:35,  6.47s/it]"]},{"name":"stdout","output_type":"stream","text":["--------\n","step 1: 不是</s>\n","--------\n","step 2: 不是\n","--------\n","step 3: 不是\n","--------\n","step 4: 不是\n","--------\n","step 5: 不是\n"]},{"name":"stderr","output_type":"stream","text":[" 22%|██▏       | 657/3000 [40:38<2:18:00,  3.53s/it]"]}],"source":["%%time\n","\n","evaluate_model(model, tokenizer, f\"{model_name}{'_' + adapter_name_or_path if adapter_name_or_path else ''}\", datasets[\"test\"])"]}],"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}

llm_toolkit/llm_utils.py

@@ -15,10 +15,11 @@ def load_model(
     dtype=torch.bfloat16,
     load_in_4bit=False,
     adapter_name_or_path=None,
+    using_llama_factory=True,
 ):
-    print(f"loading model: {model_name}")
+    print(f"loading model: {model_name} with adapter: {adapter_name_or_path}")
 
-    if adapter_name_or_path:
+    if adapter_name_or_path and using_llama_factory:
         from llamafactory.chat import ChatModel
 
         template = "llama3" if "llama-3" in model_name.lower() else "chatml"
@@ -62,6 +63,9 @@ def load_model(
         )
     )
 
+    if adapter_name_or_path:
+        model.load_adapter(adapter_name_or_path)
+
     return model, tokenizer
 
 

requirements.txt

@@ -16,3 +16,4 @@ transformers==4.41.2
 sentencepiece==0.2.0
 einops==0.8.0
 accelerate==0.32.1
+peft==0.11.1

results/mgtv-llama3_p1_full_metrics.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bd91260fe70560b3e36aa0941b0cd71f7a128c7490b7596c8aa972b45f4581c
-size 676
+oid sha256:e1c06294652630a6d1b0c05d3ca091965b6d784065978ab9a8c49402fed78d58
+size 1053

results/mgtv-llama3_p2_full_metrics.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8c2c086a75ff1255303e3336296121696f55a630f2f1930e1ed90faa53c1022
-size 542
+oid sha256:d5642a10e7386383a2620e57a762a9cf2457fd9fcd8800ba970013d23d65ca65
+size 757