show downloads

.gitignore

@@ -13,6 +13,7 @@ ch05/02_alternative_weight_loading/checkpoints
 ch05/01_main-chapter-code/model.pth
 ch05/01_main-chapter-code/model_and_optimizer.pth
 ch05/03_bonus_pretraining_on_gutenberg/model_checkpoints
+ch06/01_main-chapter-code/gpt2
 
 # Datasets
 ch02/01_main-chapter-code/number-data.txt

ch06/01_main-chapter-code/ch06.ipynb

@@ -628,7 +628,10 @@
     "    def __getitem__(self, index):\n",
     "        encoded = self.encoded_texts[index]\n",
     "        label = self.data.iloc[index][\"Label\"]\n",
-    "        return torch.tensor(encoded, dtype=torch.long), torch.tensor(label, dtype=torch.long)\n",
+    "        return (\n",
+    "            torch.tensor(encoded, dtype=torch.long),\n",
+    "            torch.tensor(label, dtype=torch.long)\n",
+    "        )\n",
     "\n",
     "    def __len__(self):\n",
     "        return len(self.data)\n",
@@ -663,7 +666,12 @@
     }
    ],
    "source": [
-    "train_dataset = SpamDataset(\"train.csv\", max_length=None, tokenizer=tokenizer)\n",
+    "train_dataset = SpamDataset(\n",
+    "    csv_file=\"train.csv\",\n",
+    "    max_length=None,\n",
+    "    tokenizer=tokenizer\n",
+    ")\n",
+    "\n",
     "print(train_dataset.max_length)"
    ]
   },
@@ -686,16 +694,24 @@
    },
    "outputs": [],
    "source": [
-    "val_dataset = SpamDataset(\"validation.csv\", max_length=train_dataset.max_length, tokenizer=tokenizer)\n",
-    "test_dataset = SpamDataset(\"test.csv\", max_length=train_dataset.max_length, tokenizer=tokenizer)"
+    "val_dataset = SpamDataset(\n",
+    "    csv_file=\"validation.csv\",\n",
+    "    max_length=train_dataset.max_length,\n",
+    "    tokenizer=tokenizer\n",
+    ")\n",
+    "test_dataset = SpamDataset(\n",
+    "    csv_file=\"test.csv\",\n",
+    "    max_length=train_dataset.max_length,\n",
+    "    tokenizer=tokenizer\n",
+    ")"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "20170d89-85a0-4844-9887-832f5d23432a",
    "metadata": {},
    "source": [
-    "- Next, we use the dataset to instantiate the data loaders, which is similar to creating the data loaders in previous chapters:"
+    "- Next, we use the dataset to instantiate the data loaders, which is similar to creating the data loaders in previous chapters"
    ]
   },
   {
@@ -787,7 +803,7 @@
    "id": "5cdd7947-7039-49bf-8a5e-c0a2f4281ca1",
    "metadata": {},
    "source": [
-    "- Lastly, let's print the total number of batches in each dataset:"
+    "- Lastly, let's print the total number of batches in each dataset"
    ]
   },
   {
@@ -880,16 +896,16 @@
    },
    "outputs": [
     {
-     "name": "stdout",
+     "name": "stderr",
      "output_type": "stream",
      "text": [
-      "File already exists and is up-to-date: gpt2/124M/checkpoint\n",
-      "File already exists and is up-to-date: gpt2/124M/encoder.json\n",
-      "File already exists and is up-to-date: gpt2/124M/hparams.json\n",
-      "File already exists and is up-to-date: gpt2/124M/model.ckpt.data-00000-of-00001\n",
-      "File already exists and is up-to-date: gpt2/124M/model.ckpt.index\n",
-      "File already exists and is up-to-date: gpt2/124M/model.ckpt.meta\n",
-      "File already exists and is up-to-date: gpt2/124M/vocab.bpe\n"
+      "checkpoint: 100%|███████████████████████████| 77.0/77.0 [00:00<00:00, 39.7kiB/s]\n",
+      "encoder.json: 100%|███████████████████████| 1.04M/1.04M [00:00<00:00, 3.25MiB/s]\n",
+      "hparams.json: 100%|█████████████████████████| 90.0/90.0 [00:00<00:00, 51.4kiB/s]\n",
+      "model.ckpt.data-00000-of-00001: 100%|███████| 498M/498M [01:00<00:00, 8.20MiB/s]\n",
+      "model.ckpt.index: 100%|███████████████████| 5.21k/5.21k [00:00<00:00, 2.34MiB/s]\n",
+      "model.ckpt.meta: 100%|██████████████████████| 471k/471k [00:00<00:00, 2.26MiB/s]\n",
+      "vocab.bpe: 100%|████████████████████████████| 456k/456k [00:00<00:00, 2.62MiB/s]\n"
      ]
     }
    ],