{
 "cells": [
 {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 296
    },
    "colab_type": "code",
    "id": "kPRcGL5Q6TWn",
    "outputId": "fe480f09-0a5b-4f8d-ebc1-b87016af0331"
   },
   "outputs": [
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {
      "tags": []
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR Finder is complete, type {learner_name}.recorder.plot() to see the graph.\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEGCAYAAABo25JHAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIiIxToVARCTGqRCIiMQ4FQIRkRj3/83RZRIp333EAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "tags": []
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "learn.lr_find()\n",
    "learn.recorder.plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 94
    },
    "colab_type": "code",
    "id": "V3RwCbgN6TWt",
    "outputId": "91840296-58fd-4399-8407-8a40087e3760"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>accuracy</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>7.849431</td>\n",
       "      <td>6.545413</td>\n",
       "      <td>0.107709</td>\n",
       "      <td>00:07</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {
      "tags": []
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "learn.fit_one_cycle(1, 1e-2, moms=(0.8,0.7)) # training only the head"
   ]
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "collapsed_sections": [],
   "name": "code1.ipynb",
   "provenance": [],
   "version": "0.3.2"
  },
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}