annotated_deep_learning_paper_implementations/labml_nn/hypernetworks/experiment.ipynb

{
 "nbformat": 4,
 "nbformat_minor": 0,
 "metadata": {
  "colab": {
   "name": "HyperLSTM",
   "provenance": [],
   "collapsed_sections": []
  },
  "kernelspec": {
   "name": "python3",
   "display_name": "Python 3"
  },
  "accelerator": "GPU"
 },
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "AYV_dMVDxyc2"
   },
   "source": [
    "[![Github](https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social)](https://github.com/labmlai/annotated_deep_learning_paper_implementations)\n",
    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/hypernetworks/experiment.ipynb)                    \n",
    "\n",
    "## HyperLSTM\n",
    "\n",
    "This is an experiment training Shakespear dataset with HyperLSTM from paper HyperNetworks."
   ]
  },
  {
   "cell_type": "code",
   "metadata": {
    "id": "ZCzmCrAIVg0L"
   },
   "source": [
    "!pip install labml-nn"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {
    "id": "0hJXx_g0wS2C"
   },
   "source": [
    "from labml import experiment\n",
    "from labml_nn.hypernetworks.experiment import Configs"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 255
    },
    "id": "WQ8VGpMGwZuj",
    "outputId": "5833cc50-26a8-496e-e729-88f42b3f4651"
   },
   "source": [
    "# Create experiment\n",
    "experiment.create(name=\"hyper_lstm\", comment='')\n",
    "# Create configs\n",
    "conf = Configs()\n",
    "# Load configurations\n",
    "experiment.configs(conf,\n",
    "                    # A dictionary of configurations to override\n",
    "                    {'tokenizer': 'character',\n",
    "                    'text': 'tiny_shakespeare',\n",
    "                    'optimizer.learning_rate': 2.5e-4,\n",
    "                    'optimizer.optimizer': 'Adam',\n",
    "                    'prompt': 'It is',\n",
    "                    'prompt_separator': '',\n",
    "\n",
    "                    'rnn_model': 'hyper_lstm',\n",
    "\n",
    "                    'train_loader': 'shuffled_train_loader',\n",
    "                    'valid_loader': 'shuffled_valid_loader',\n",
    "\n",
    "                    'seq_len': 512,\n",
    "                    'epochs': 128,\n",
    "                    'batch_size': 2,\n",
    "                    'inner_iterations': 25})\n",
    "\n",
    "\n",
    "# Set models for saving and loading\n",
    "experiment.add_pytorch_models({'model': conf.model})\n",
    "\n",
    "conf.init()"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 425
    },
    "id": "f07vAOaHwumr",
    "outputId": "6b51205e-3852-4dce-f7a7-f3ba4066ba21"
   },
   "source": [
    "# Start the experiment\n",
    "with experiment.start():\n",
    "    # `TrainValidConfigs.run`\n",
    "    conf.run()"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "metadata": {
    "id": "crH6MzKmw-SY"
   },
   "source": [
    ""
   ],
   "outputs": [],
   "execution_count": null
  }
 ]
}