Train_transformer_resume.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from src.nn.train import train, load_checkpoint\n",
    "from src.dataset.dataset import SparkifyDataset\n",
    "from src.nn.Transformer import TransformerModel\n",
    "from torch.optim.adam import Adam"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "checkpoint_path = \"./checkpoints/sparkify_transformer\"\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "model, opt, seen_epochs, train_ds, test_ds, writer, checkpoint_path, ignore_index, cross_entropy_weights = load_checkpoint(\n",
    "    checkpoint_path,\n",
    "    TransformerModel,\n",
    "    Adam,\n",
    "    device=device\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Seen epochs: 1670025\n"
     ]
    }
   ],
   "source": [
    "print(f\"Seen epochs: {seen_epochs}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "target_epochs = 1000 * 1000 * 3\n",
    "batch_size = 64\n",
    "test_batch_size = 64"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "febc3989d6db4fcbbe7375a76910f640",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/1329975 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/run/media/john/Secondary/Documents/Cornell/Spring 2024/ORIE 4741 Learning From Data/Project/proj/lib64/python3.11/site-packages/torch/nested/__init__.py:166: UserWarning: The PyTorch API of nested tensors is in prototype stage and will change in the near future. (Triggered internally at ../aten/src/ATen/NestedTensorImpl.cpp:177.)\n",
      "  return _nested.nested_tensor(\n"
     ]
    }
   ],
   "source": [
    "train(\n",
    "    train_data=train_ds,\n",
    "    test_data=test_ds,\n",
    "    model=model,\n",
    "    target_epochs=target_epochs,\n",
    "    seen_epochs=seen_epochs,\n",
    "    batch_size=batch_size,\n",
    "    test_batch_size=test_batch_size,\n",
    "    optm=opt,\n",
    "    writer=writer,\n",
    "    checkpoint_path=checkpoint_path,\n",
    "    device=device,\n",
    "    cross_entropy_weights=cross_entropy_weights,\n",
    "    save_every_n=5000\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}