llama.ipynb

llama.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "mount_file_id": "16eiLkNtIBMiShmr5fm73TVz62HkMcStE",
      "authorship_tag": "ABX9TyPxXP4j+tZj+/7gU6TQj2lR",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/alucard001/ed115328a82865961d020d46387cfd47/llama.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "rXtDrQpRKPM3"
      },
      "outputs": [],
      "source": [
        "# !pip install torch torchvision torchaudio\n",
        "# !pip install -r drive/MyDrive/llama/requirements.txt"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import torch\n",
        "print(\"Pytorch version: \", torch.__version__)\n",
        "print(\"which cuda was your PyTorch built?:\", torch.version.cuda)\n",
        "print(\"Is torch.cuda available?\", torch.cuda.is_available())\n",
        "print(\"torch CUDA device name: \", torch.cuda.get_device_name(0))"
      ],
      "metadata": {
        "id": "yGLpIrxPZLO7",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "18488a85-445f-4d16-91cf-a4e3dd4437cc"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Pytorch version:  2.0.1+cu118\n",
            "which cuda was your PyTorch built?: 11.8\n",
            "Is torch.cuda available? True\n",
            "torch CUDA device name:  Tesla T4\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!torchrun --nproc_per_node 1 example_text_completion.py \\\n",
        "    --ckpt_dir drive/MyDrive/llama/llama-2-7b/ \\\n",
        "    --tokenizer_path tokenizer.model \\\n",
        "    --max_seq_len 128 --max_batch_size 4"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5-BGd2HmbHS_",
        "outputId": "828f5d9b-b03d-4261-e428-20518afa9ddc"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "> initializing model parallel with size 1\n",
            "> initializing ddp with size 1\n",
            "> initializing pipeline with size 1\n",
            "ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -9) local_rank: 0 (pid: 1950) of binary: /usr/bin/python3\n",
            "Traceback (most recent call last):\n",
            "  File \"/usr/local/bin/torchrun\", line 8, in <module>\n",
            "    sys.exit(main())\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py\", line 346, in wrapper\n",
            "    return f(*args, **kwargs)\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/torch/distributed/run.py\", line 794, in main\n",
            "    run(args)\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/torch/distributed/run.py\", line 785, in run\n",
            "    elastic_launch(\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/torch/distributed/launcher/api.py\", line 134, in __call__\n",
            "    return launch_agent(self._config, self._entrypoint, list(args))\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/torch/distributed/launcher/api.py\", line 250, in launch_agent\n",
            "    raise ChildFailedError(\n",
            "torch.distributed.elastic.multiprocessing.errors.ChildFailedError: \n",
            "=====================================================\n",
            "example_text_completion.py FAILED\n",
            "-----------------------------------------------------\n",
            "Failures:\n",
            "  <NO_OTHER_FAILURES>\n",
            "-----------------------------------------------------\n",
            "Root Cause (first observed failure):\n",
            "[0]:\n",
            "  time      : 2023-07-22_10:24:43\n",
            "  host      : f01c16657d58\n",
            "  rank      : 0 (local_rank: 0)\n",
            "  exitcode  : -9 (pid: 1950)\n",
            "  error_file: <N/A>\n",
            "  traceback : Signal 9 (SIGKILL) received by PID 1950\n",
            "=====================================================\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "LLcsZiN0bTQ1"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}