Edited using Colaboratory (#3601)

notebooks/04-transformers-text-classification.ipynb

@@ -6,8 +6,7 @@
       "name": "04-transformers-text-classification.ipynb",
       "provenance": [],
       "collapsed_sections": [],
-      "toc_visible": true,
-      "include_colab_link": true
+      "toc_visible": true
     },
     "kernelspec": {
       "name": "python3",
@@ -16,16 +15,6 @@
     "accelerator": "GPU"
   },
   "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "view-in-github",
-        "colab_type": "text"
-      },
-      "source": [
-        "<a href=\"https://colab.research.google.com/github/PytorchLightning/pytorch-lightning/blob/master/notebooks/04-transformers-text-classification.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -42,9 +31,10 @@
         "---\n",
         "  - Give us a ⭐ [on Github](https://www.github.com/PytorchLightning/pytorch-lightning/)\n",
         "  - Check out [the documentation](https://pytorch-lightning.readthedocs.io/en/latest/)\n",
+        "  - Ask a question on [the forum](https://forums.pytorchlightning.ai/)\n",
         "  - Join us [on Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)\n",
         "\n",
-        "  - [HuggingFace nlp](https://github.com/huggingface/nlp)\n",
+        "  - [HuggingFace datasets](https://github.com/huggingface/datasets)\n",
         "  - [HuggingFace transformers](https://github.com/huggingface/transformers)"
       ]
     },
@@ -83,7 +73,7 @@
         "from datetime import datetime\n",
         "from typing import Optional\n",
         "\n",
-        "import nlp\n",
+        "import datasets\n",
         "import numpy as np\n",
         "import pytorch_lightning as pl\n",
         "import torch\n",
@@ -97,7 +87,7 @@
         "    glue_compute_metrics\n",
         ")"
       ],
-      "execution_count": null,
+      "execution_count": 2,
       "outputs": []
     },
     {
@@ -147,7 +137,7 @@
         "    }\n",
         "\n",
         "    loader_columns = [\n",
-        "        'nlp_idx',\n",
+        "        'datasets_idx',\n",
         "        'input_ids',\n",
         "        'token_type_ids',\n",
         "        'attention_mask',\n",
@@ -177,7 +167,7 @@
         "        self.tokenizer = AutoTokenizer.from_pretrained(self.model_name_or_path, use_fast=True)\n",
         "\n",
         "    def setup(self, stage):\n",
-        "        self.dataset = nlp.load_dataset('glue', self.task_name)\n",
+        "        self.dataset = datasets.load_dataset('glue', self.task_name)\n",
         "\n",
         "        for split in self.dataset.keys():\n",
         "            self.dataset[split] = self.dataset[split].map(\n",
@@ -191,7 +181,7 @@
         "        self.eval_splits = [x for x in self.dataset.keys() if 'validation' in x]\n",
         "\n",
         "    def prepare_data(self):\n",
-        "        nlp.load_dataset('glue', self.task_name)\n",
+        "        datasets.load_dataset('glue', self.task_name)\n",
         "        AutoTokenizer.from_pretrained(self.model_name_or_path, use_fast=True)\n",
         "    \n",
         "    def train_dataloader(self):\n",
@@ -230,7 +220,7 @@
         "\n",
         "        return features"
       ],
-      "execution_count": null,
+      "execution_count": 3,
       "outputs": []
     },
     {
@@ -297,7 +287,7 @@
         "\n",
         "        self.config = AutoConfig.from_pretrained(model_name_or_path, num_labels=num_labels)\n",
         "        self.model = AutoModelForSequenceClassification.from_pretrained(model_name_or_path, config=self.config)\n",
-        "        self.metric = nlp.load_metric(\n",
+        "        self.metric = datasets.load_metric(\n",
         "            'glue',\n",
         "            self.hparams.task_name,\n",
         "            experiment_id=datetime.now().strftime(\"%d-%m-%Y_%H-%M-%S\")\n",
@@ -335,7 +325,7 @@
         "                if i == 0:\n",
         "                    result = pl.EvalResult(checkpoint_on=loss)\n",
         "                result.log(f'val_loss_{split}', loss, prog_bar=True)\n",
-        "                split_metrics = {f\"{k}_{split}\": v for k, v in self.metric.compute(preds, labels).items()}\n",
+        "                split_metrics = {f\"{k}_{split}\": v for k, v in self.metric.compute(predictions=preds, references=labels).items()}\n",
         "                result.log_dict(split_metrics, prog_bar=True)\n",
         "            return result\n",
         "\n",
@@ -344,7 +334,7 @@
         "        loss = torch.stack([x['loss'] for x in outputs]).mean()\n",
         "        result = pl.EvalResult(checkpoint_on=loss)\n",
         "        result.log('val_loss', loss, prog_bar=True)\n",
-        "        result.log_dict(self.metric.compute(preds, labels), prog_bar=True)\n",
+        "        result.log_dict(self.metric.compute(predictions=preds, references=labels), prog_bar=True)\n",
         "        return result\n",
         "\n",
         "    def setup(self, stage):\n",
@@ -394,7 +384,7 @@
         "        parser.add_argument(\"--weight_decay\", default=0.0, type=float)\n",
         "        return parser"
       ],
-      "execution_count": null,
+      "execution_count": 5,
       "outputs": []
     },
     {
@@ -434,7 +424,7 @@
         "    trainer = pl.Trainer.from_argparse_args(args)\n",
         "    return dm, model, trainer"
       ],
-      "execution_count": null,
+      "execution_count": 6,
       "outputs": []
     },
     {
@@ -553,4 +543,4 @@
       "outputs": []
     }
   ]
-}
+}