CNN/notebook.ipynb

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"gpuType":"T4","authorship_tag":"ABX9TyMEUDJnXVT44WSfGZyI93z0"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU"},"cells":[{"cell_type":"code","execution_count":1,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"0nn9f5w-C9cx","executionInfo":{"status":"ok","timestamp":1754361178465,"user_tz":-345,"elapsed":833,"user":{"displayName":"Sandesh Upreti","userId":"13536213929194699967"}},"outputId":"dd7af284-2a35-46fc-ea2e-243115b794f1"},"outputs":[{"output_type":"stream","name":"stdout","text":["Cloning into 'SigExt'...\n","remote: Enumerating objects: 17, done.\u001b[K\n","remote: Counting objects: 100% (17/17), done.\u001b[K\n","remote: Compressing objects: 100% (16/16), done.\u001b[K\n","remote: Total 17 (delta 1), reused 14 (delta 1), pack-reused 0 (from 0)\u001b[K\n","Receiving objects: 100% (17/17), 18.86 KiB | 18.86 MiB/s, done.\n","Resolving deltas: 100% (1/1), done.\n"]}],"source":["!git clone https://github.com/amazon-science/SigExt.git"]},{"cell_type":"code","source":["%cd SigExt/src"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"r4Z0CreeDbji","executionInfo":{"status":"ok","timestamp":1754361199823,"user_tz":-345,"elapsed":16,"user":{"displayName":"Sandesh Upreti","userId":"13536213929194699967"}},"outputId":"9542f941-a5c2-4c7f-84fd-7b1dfab73c4b"},"execution_count":2,"outputs":[{"output_type":"stream","name":"stdout","text":["/content/SigExt/src\n"]}]},{"cell_type":"code","source":["!pip install jsonlines rake_nltk"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"FEqg5huCFIw-","executionInfo":{"status":"ok","timestamp":1754361319194,"user_tz":-345,"elapsed":4942,"user":{"displayName":"Sandesh Upreti","userId":"13536213929194699967"}},"outputId":"08938dc5-ff95-4008-c234-0418ee035bff"},"execution_count":6,"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: jsonlines in /usr/local/lib/python3.11/dist-packages (4.0.0)\n","Collecting rake_nltk\n","  Downloading rake_nltk-1.0.6-py3-none-any.whl.metadata (6.4 kB)\n","Requirement already satisfied: attrs>=19.2.0 in /usr/local/lib/python3.11/dist-packages (from jsonlines) (25.3.0)\n","Requirement already satisfied: nltk<4.0.0,>=3.6.2 in /usr/local/lib/python3.11/dist-packages (from rake_nltk) (3.9.1)\n","Requirement already satisfied: click in /usr/local/lib/python3.11/dist-packages (from nltk<4.0.0,>=3.6.2->rake_nltk) (8.2.1)\n","Requirement already satisfied: joblib in /usr/local/lib/python3.11/dist-packages (from nltk<4.0.0,>=3.6.2->rake_nltk) (1.5.1)\n","Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.11/dist-packages (from nltk<4.0.0,>=3.6.2->rake_nltk) (2024.11.6)\n","Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (from nltk<4.0.0,>=3.6.2->rake_nltk) (4.67.1)\n","Downloading rake_nltk-1.0.6-py3-none-any.whl (9.1 kB)\n","Installing collected packages: rake_nltk\n","Successfully installed rake_nltk-1.0.6\n"]}]},{"cell_type":"code","source":["#add below lines on prepare_data.py after line 18\n","#nltk.download('stopwords')\n","#nltk.download('punkt_tab')"],"metadata":{"id":"nBqBy5Y_Frl3"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["!python3 prepare_data.py --dataset cnn --output_dir /content/SigExt/experiments/cnn_dataset/"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"BTzeyFnpE3uE","executionInfo":{"status":"ok","timestamp":1754361636892,"user_tz":-345,"elapsed":64314,"user":{"displayName":"Sandesh Upreti","userId":"13536213929194699967"}},"outputId":"1d481f48-d24b-4bc4-bb7e-f0bf18bd81e3"},"execution_count":9,"outputs":[{"output_type":"stream","name":"stdout","text":["[nltk_data] Downloading package stopwords to /root/nltk_data...\n","[nltk_data]   Package stopwords is already up-to-date!\n","[nltk_data] Downloading package punkt_tab to /root/nltk_data...\n","[nltk_data]   Unzipping tokenizers/punkt_tab.zip.\n","100% 200/200 [00:05<00:00, 39.02it/s]\n","100% 1000/1000 [00:28<00:00, 35.45it/s]\n","100% 500/500 [00:15<00:00, 31.31it/s]\n"]}]},{"cell_type":"code","source":["!pip install pytorch_lightning"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"NKCpx2WoG6ev","executionInfo":{"status":"ok","timestamp":1754361862067,"user_tz":-345,"elapsed":114254,"user":{"displayName":"Sandesh Upreti","userId":"13536213929194699967"}},"outputId":"53f9167d-0130-4392-c8e7-b5e1654674da"},"execution_count":11,"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting pytorch_lightning\n","  Downloading pytorch_lightning-2.5.2-py3-none-any.whl.metadata (21 kB)\n","Requirement already satisfied: torch>=2.1.0 in /usr/local/lib/python3.11/dist-packages (from pytorch_lightning) (2.6.0+cu124)\n","Requirement already satisfied: tqdm>=4.57.0 in /usr/local/lib/python3.11/dist-packages (from pytorch_lightning) (4.67.1)\n","Requirement already satisfied: PyYAML>=5.4 in /usr/local/lib/python3.11/dist-packages (from pytorch_lightning) (6.0.2)\n","Requirement already satisfied: fsspec>=2022.5.0 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]>=2022.5.0->pytorch_lightning) (2025.3.0)\n","Collecting torchmetrics>=0.7.0 (from pytorch_lightning)\n","  Downloading torchmetrics-1.8.0-py3-none-any.whl.metadata (21 kB)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from pytorch_lightning) (25.0)\n","Requirement already satisfied: typing-extensions>=4.4.0 in /usr/local/lib/python3.11/dist-packages (from pytorch_lightning) (4.14.1)\n","Collecting lightning-utilities>=0.10.0 (from pytorch_lightning)\n","  Downloading lightning_utilities-0.15.1-py3-none-any.whl.metadata (5.7 kB)\n","Requirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]>=2022.5.0->pytorch_lightning) (3.12.14)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.11/dist-packages (from lightning-utilities>=0.10.0->pytorch_lightning) (75.2.0)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from torch>=2.1.0->pytorch_lightning) (3.18.0)\n","Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch>=2.1.0->pytorch_lightning) (3.5)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch>=2.1.0->pytorch_lightning) (3.1.6)\n","Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch>=2.1.0->pytorch_lightning)\n","  Downloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n","Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch>=2.1.0->pytorch_lightning)\n","  Downloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n","Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch>=2.1.0->pytorch_lightning)\n","  Downloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n","Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch>=2.1.0->pytorch_lightning)\n","  Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n","Collecting nvidia-cublas-cu12==12.4.5.8 (from torch>=2.1.0->pytorch_lightning)\n","  Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n","Collecting nvidia-cufft-cu12==11.2.1.3 (from torch>=2.1.0->pytorch_lightning)\n","  Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n","Collecting nvidia-curand-cu12==10.3.5.147 (from torch>=2.1.0->pytorch_lightning)\n","  Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n","Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch>=2.1.0->pytorch_lightning)\n","  Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n","Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch>=2.1.0->pytorch_lightning)\n","  Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n","Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch>=2.1.0->pytorch_lightning) (0.6.2)\n","Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch>=2.1.0->pytorch_lightning) (2.21.5)\n","Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.1.0->pytorch_lightning) (12.4.127)\n","Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch>=2.1.0->pytorch_lightning)\n","  Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n","Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch>=2.1.0->pytorch_lightning) (3.2.0)\n","Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch>=2.1.0->pytorch_lightning) (1.13.1)\n","Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch>=2.1.0->pytorch_lightning) (1.3.0)\n","Requirement already satisfied: numpy>1.20.0 in /usr/local/lib/python3.11/dist-packages (from torchmetrics>=0.7.0->pytorch_lightning) (2.0.2)\n","Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch_lightning) (2.6.1)\n","Requirement already satisfied: aiosignal>=1.4.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch_lightning) (1.4.0)\n","Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch_lightning) (25.3.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch_lightning) (1.7.0)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch_lightning) (6.6.3)\n","Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch_lightning) (0.3.2)\n","Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch_lightning) (1.20.1)\n","Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch>=2.1.0->pytorch_lightning) (3.0.2)\n","Requirement already satisfied: idna>=2.0 in /usr/local/lib/python3.11/dist-packages (from yarl<2.0,>=1.17.0->aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch_lightning) (3.10)\n","Downloading pytorch_lightning-2.5.2-py3-none-any.whl (825 kB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m825.4/825.4 kB\u001b[0m \u001b[31m21.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading lightning_utilities-0.15.1-py3-none-any.whl (29 kB)\n","Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (13.8 MB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.8/13.8 MB\u001b[0m \u001b[31m41.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (24.6 MB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.6/24.6 MB\u001b[0m \u001b[31m21.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (883 kB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m883.7/883.7 kB\u001b[0m \u001b[31m33.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m798.8 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m14.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m71.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading torchmetrics-1.8.0-py3-none-any.whl (981 kB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m981.9/981.9 kB\u001b[0m \u001b[31m58.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hInstalling collected packages: nvidia-nvjitlink-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, lightning-utilities, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, torchmetrics, pytorch_lightning\n","  Attempting uninstall: nvidia-nvjitlink-cu12\n","    Found existing installation: nvidia-nvjitlink-cu12 12.5.82\n","    Uninstalling nvidia-nvjitlink-cu12-12.5.82:\n","      Successfully uninstalled nvidia-nvjitlink-cu12-12.5.82\n","  Attempting uninstall: nvidia-curand-cu12\n","    Found existing installation: nvidia-curand-cu12 10.3.6.82\n","    Uninstalling nvidia-curand-cu12-10.3.6.82:\n","      Successfully uninstalled nvidia-curand-cu12-10.3.6.82\n","  Attempting uninstall: nvidia-cufft-cu12\n","    Found existing installation: nvidia-cufft-cu12 11.2.3.61\n","    Uninstalling nvidia-cufft-cu12-11.2.3.61:\n","      Successfully uninstalled nvidia-cufft-cu12-11.2.3.61\n","  Attempting uninstall: nvidia-cuda-runtime-cu12\n","    Found existing installation: nvidia-cuda-runtime-cu12 12.5.82\n","    Uninstalling nvidia-cuda-runtime-cu12-12.5.82:\n","      Successfully uninstalled nvidia-cuda-runtime-cu12-12.5.82\n","  Attempting uninstall: nvidia-cuda-nvrtc-cu12\n","    Found existing installation: nvidia-cuda-nvrtc-cu12 12.5.82\n","    Uninstalling nvidia-cuda-nvrtc-cu12-12.5.82:\n","      Successfully uninstalled nvidia-cuda-nvrtc-cu12-12.5.82\n","  Attempting uninstall: nvidia-cuda-cupti-cu12\n","    Found existing installation: nvidia-cuda-cupti-cu12 12.5.82\n","    Uninstalling nvidia-cuda-cupti-cu12-12.5.82:\n","      Successfully uninstalled nvidia-cuda-cupti-cu12-12.5.82\n","  Attempting uninstall: nvidia-cublas-cu12\n","    Found existing installation: nvidia-cublas-cu12 12.5.3.2\n","    Uninstalling nvidia-cublas-cu12-12.5.3.2:\n","      Successfully uninstalled nvidia-cublas-cu12-12.5.3.2\n","  Attempting uninstall: nvidia-cusparse-cu12\n","    Found existing installation: nvidia-cusparse-cu12 12.5.1.3\n","    Uninstalling nvidia-cusparse-cu12-12.5.1.3:\n","      Successfully uninstalled nvidia-cusparse-cu12-12.5.1.3\n","  Attempting uninstall: nvidia-cudnn-cu12\n","    Found existing installation: nvidia-cudnn-cu12 9.3.0.75\n","    Uninstalling nvidia-cudnn-cu12-9.3.0.75:\n","      Successfully uninstalled nvidia-cudnn-cu12-9.3.0.75\n","  Attempting uninstall: nvidia-cusolver-cu12\n","    Found existing installation: nvidia-cusolver-cu12 11.6.3.83\n","    Uninstalling nvidia-cusolver-cu12-11.6.3.83:\n","      Successfully uninstalled nvidia-cusolver-cu12-11.6.3.83\n","Successfully installed lightning-utilities-0.15.1 nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupti-cu12-12.4.127 nvidia-cuda-nvrtc-cu12-12.4.127 nvidia-cuda-runtime-cu12-12.4.127 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nvjitlink-cu12-12.4.127 pytorch_lightning-2.5.2 torchmetrics-1.8.0\n"]}]},{"cell_type":"code","source":["!pip install rouge-score"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"NpR9ogauHgDL","executionInfo":{"status":"ok","timestamp":1754361953458,"user_tz":-345,"elapsed":12757,"user":{"displayName":"Sandesh Upreti","userId":"13536213929194699967"}},"outputId":"9132c1b8-d88f-4d17-b1b2-a806c79a3b5b"},"execution_count":15,"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting rouge-score\n","  Downloading rouge_score-0.1.2.tar.gz (17 kB)\n","  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n","Requirement already satisfied: absl-py in /usr/local/lib/python3.11/dist-packages (from rouge-score) (1.4.0)\n","Requirement already satisfied: nltk in /usr/local/lib/python3.11/dist-packages (from rouge-score) (3.9.1)\n","Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (from rouge-score) (2.0.2)\n","Requirement already satisfied: six>=1.14.0 in /usr/local/lib/python3.11/dist-packages (from rouge-score) (1.17.0)\n","Requirement already satisfied: click in /usr/local/lib/python3.11/dist-packages (from nltk->rouge-score) (8.2.1)\n","Requirement already satisfied: joblib in /usr/local/lib/python3.11/dist-packages (from nltk->rouge-score) (1.5.1)\n","Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.11/dist-packages (from nltk->rouge-score) (2024.11.6)\n","Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (from nltk->rouge-score) (4.67.1)\n","Building wheels for collected packages: rouge-score\n","  Building wheel for rouge-score (setup.py) ... \u001b[?25l\u001b[?25hdone\n","  Created wheel for rouge-score: filename=rouge_score-0.1.2-py3-none-any.whl size=24934 sha256=becb3ce31ef09bf2ec240fc1cf1b2b5d0614b6340219385d9bf784ff65d2045e\n","  Stored in directory: /root/.cache/pip/wheels/1e/19/43/8a442dc83660ca25e163e1bd1f89919284ab0d0c1475475148\n","Successfully built rouge-score\n","Installing collected packages: rouge-score\n","Successfully installed rouge-score-0.1.2\n"]}]},{"cell_type":"code","source":["!python3 train_longformer_extractor_context.py \\\n","  --dataset_dir /content/SigExt/experiments/cnn_dataset \\    #put the output dir locaation where u processed the dataset.\n","  --checkpoint_dir  /content/SigExt/experiments/cnn_extractor_model/"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"qSRryiVdGpWq","executionInfo":{"status":"ok","timestamp":1754362579687,"user_tz":-345,"elapsed":624436,"user":{"displayName":"Sandesh Upreti","userId":"13536213929194699967"}},"outputId":"899b71b3-c254-4742-e627-81f40cc277fb"},"execution_count":16,"outputs":[{"output_type":"stream","name":"stdout","text":["Seed set to 42\n","config.json: 100% 694/694 [00:00<00:00, 3.80MB/s]\n","vocab.json: 899kB [00:00, 17.4MB/s]\n","merges.txt: 456kB [00:00, 83.0MB/s]\n","tokenizer.json: 1.36MB [00:00, 54.4MB/s]\n","INFO:absl:Using default tokenizer.\n","process data: 100% 1000/1000 [04:42<00:00,  3.54it/s]\n","INFO:root:keyword ratio 0.17427932856179468\n","INFO:root:Dataset size: 1000\n","INFO:absl:Using default tokenizer.\n","process data: 100% 200/200 [01:01<00:00,  3.24it/s]\n","INFO:root:keyword ratio 0.21349087988987037\n","INFO:root:Dataset size: 200\n","2025-08-05 02:51:57.830196: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n","WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n","E0000 00:00:1754362318.107159    4039 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n","E0000 00:00:1754362318.183019    4039 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n","2025-08-05 02:51:58.742622: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n","To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n","pytorch_model.bin: 100% 597M/597M [00:10<00:00, 59.5MB/s]\n","Some weights of LongformerForTokenClassification were not initialized from the model checkpoint at allenai/longformer-base-4096 and are newly initialized: ['classifier.bias', 'classifier.weight']\n","You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n","GPU available: True (cuda), used: True\n","TPU available: False, using: 0 TPU cores\n","HPU available: False, using: 0 HPUs\n","Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/1\n","----------------------------------------------------------------------------------------------------\n","distributed_backend=nccl\n","All distributed processes registered. Starting with 1 processes\n","----------------------------------------------------------------------------------------------------\n","\n","model.safetensors:   0% 0.00/597M [00:00<?, ?B/s]LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n","Loading `train_dataloader` to estimate number of stepping batches.\n","model.safetensors:   9% 54.4M/597M [00:02<00:21, 25.8MB/s]\n","  | Name | Type                             | Params | Mode\n","-----------------------------------------------------------------\n","0 | clf  | LongformerForTokenClassification | 148 M  | eval\n","-----------------------------------------------------------------\n","148 M     Trainable params\n","0         Non-trainable params\n","148 M     Total params\n","592.282   Total estimated model params size (MB)\n","0         Modules in train mode\n","252       Modules in eval mode\n","Sanity Checking: |          | 0/? [00:00<?, ?it/s]/usr/local/lib/python3.11/dist-packages/pytorch_lightning/trainer/connectors/data_connector.py:476: Your `val_dataloader`'s sampler has shuffling enabled, it is strongly recommended that you turn shuffling off for val/test dataloaders.\n","Sanity Checking DataLoader 0:   0% 0/2 [00:00<?, ?it/s]Input ids are automatically padded to be a multiple of `config.attention_window`: 512\n","model.safetensors: 100% 597M/597M [00:08<00:00, 71.7MB/s]\n","Epoch 0:  38% 380/1000 [03:45<06:08,  1.68it/s, v_num=0]\n","Detected KeyboardInterrupt, attempting graceful shutdown ...\n","Epoch 0:  38% 380/1000 [03:56<06:26,  1.61it/s, v_num=0]\n"]}]}]}