{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7af2ca72",
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "0684c0ff",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = torch.tensor([[1.0],[2.0],[3.0]])\n",
    "y = torch.tensor([[4.0],[5.0],[6.0]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "1078a0d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "w = torch.randn(1, requires_grad=True)\n",
    "b = torch.randn(1, requires_grad=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "6d7c95c5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.4485014081001282 3.9534966945648193\n"
     ]
    }
   ],
   "source": [
    "for _ in range(100):\n",
    "    y_pred = X @ w + b\n",
    "    loss = ((y_pred - y) ** 2).mean()\n",
    "    loss.backward()\n",
    "    with torch.no_grad():\n",
    "        w -= 0.05 * w.grad\n",
    "        b -= 0.05 * w.grad\n",
    "        w.grad.zero_()\n",
    "        b.grad.zero_()\n",
    "\n",
    "print(w.item(),b.item())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b23bda3c",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1b6fcc44",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv (3.11.15.final.0)",
   "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": "3.11.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}