competition/12b_InternLM_Push_LoRA_to_hub.ipynb

{"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":"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":4,"metadata":{},"output_type":"execute_result"}],"source":["from dotenv import find_dotenv, load_dotenv\n","\n","found_dotenv = find_dotenv(\".env\")\n","\n","if len(found_dotenv) == 0:\n","    found_dotenv = find_dotenv(\".env.example\")\n","print(f\"loading env vars from: {found_dotenv}\")\n","load_dotenv(found_dotenv, override=True)"]},{"cell_type":"code","execution_count":5,"metadata":{"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":6,"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 4.51 ms, sys: 7.82 ms, total: 12.3 ms\n","Wall time: 652 ms\n"]}],"source":["%%time\n","!python --version\n","!pip show flash-attn"]},{"cell_type":"code","execution_count":7,"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":8,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["loading model: llama-factory/saves/internlm2_5_7b/lora/sft_bf16_p2_full/checkpoint-88 with adapter: None\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"59cbac92c15441b8b96eeb2079d80a9f","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 2.49 s, sys: 5.85 s, total: 8.34 s\n","Wall time: 27.5 s\n"]}],"source":["%%time\n","\n","# model, tokenizer = load_model(model_name, adapter_name_or_path=adapter_name_or_path, using_llama_factory=False)\n","model, tokenizer = load_model(adapter_name_or_path, using_llama_factory=False)"]},{"cell_type":"code","execution_count":9,"metadata":{},"outputs":[{"name":"stderr","output_type":"stream","text":["/Users/inflaton/anaconda3/envs/logical-reasoning/lib/python3.11/site-packages/transformers/integrations/peft.py:399: FutureWarning: The `active_adapter` method is deprecated and will be removed in a future version.\n","  warnings.warn(\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"6a97d694bb2c45288969b8f4806e9db3","version_major":2,"version_minor":0},"text/plain":["adapter_model.safetensors:   0%|          | 0.00/37.8M [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"text/plain":["CommitInfo(commit_url='https://huggingface.co/inflaton-ai/InternLM_2_5-7b_LoRA-Adapter/commit/822b89e129372ed5bc8372489ff6dcfef7d19cd7', commit_message='Upload InternLM2ForCausalLM', commit_description='', oid='822b89e129372ed5bc8372489ff6dcfef7d19cd7', pr_url=None, pr_revision=None, pr_num=None)"]},"execution_count":9,"metadata":{},"output_type":"execute_result"}],"source":["model.push_to_hub(\"inflaton-ai/InternLM_2_5-7b_LoRA-Adapter\")"]},{"cell_type":"code","execution_count":10,"metadata":{},"outputs":[],"source":["del model, tokenizer"]},{"cell_type":"code","execution_count":12,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["loading model: internlm/internlm2_5-7b-chat-1m with adapter: inflaton-ai/InternLM_2_5-7b_LoRA-Adapter\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"8e5a9c51fcb44a2e97ebcf0594a68938","version_major":2,"version_minor":0},"text/plain":["Loading checkpoint shards:   0%|          | 0/8 [00:00<?, ?it/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"105a5fdab3534197b34cf5e4d9ed47b3","version_major":2,"version_minor":0},"text/plain":["adapter_config.json:   0%|          | 0.00/679 [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"55bcfc7ea08e4b43aab7796ba33a32bd","version_major":2,"version_minor":0},"text/plain":["adapter_model.safetensors:   0%|          | 0.00/37.8M [00:00<?, ?B/s]"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["CPU times: user 3.06 s, sys: 5.04 s, total: 8.11 s\n","Wall time: 31.6 s\n"]}],"source":["%%time\n","\n","model, tokenizer = load_model(model_name, adapter_name_or_path=\"inflaton-ai/InternLM_2_5-7b_LoRA-Adapter\", using_llama_factory=False)\n","# model, tokenizer = load_model(\"inflaton-ai/InternLM_2_5-7b_LoRA-Adapter\", using_llama_factory=False)"]},{"cell_type":"code","execution_count":13,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["loading train/test data files\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"c01335f1a61e4b589b7c33978db1e8c6","version_major":2,"version_minor":0},"text/plain":["Map:   0%|          | 0/25000 [00:00<?, ? examples/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"1e1c242ae44b4a65b7683e8918174989","version_major":2,"version_minor":0},"text/plain":["Map:   0%|          | 0/3000 [00:00<?, ? examples/s]"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["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":14,"metadata":{},"outputs":[{"name":"stderr","output_type":"stream","text":["/Users/inflaton/anaconda3/envs/logical-reasoning/lib/python3.11/site-packages/transformers/generation/utils.py:1513: UserWarning: The operator 'aten::isin.Tensor_Tensor_out' is not currently supported on the MPS backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at /Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/mps/MPSFallback.mm:13.)\n","  if eos_token_id is not None and torch.isin(elements=eos_token_id, test_elements=pad_token_id).any():\n"]},{"name":"stdout","output_type":"stream","text":["是\n","CPU times: user 579 ms, sys: 330 ms, total: 909 ms\n","Wall time: 2.86 s\n"]}],"source":["%%time\n","\n","prompt1 = datasets[\"test\"][\"prompt\"][1000]\n","\n","gen_kwargs = {\"max_length\": 4096, \"do_sample\": True, \"top_k\": 1}\n","with torch.no_grad():\n","    inputs = tokenizer(\n","        [prompt1],\n","        return_tensors=\"pt\",\n","    ).to(device)\n","    outputs = model.generate(**inputs, **gen_kwargs)\n","    outputs = outputs[:, inputs['input_ids'].shape[1]:]\n","    print(tokenizer.decode(outputs[0], skip_special_tokens=True))"]}],"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}