diff --git "a/DynamicPadding.ipynb" "b/DynamicPadding.ipynb"
new file mode 100644--- /dev/null
+++ "b/DynamicPadding.ipynb"
@@ -0,0 +1,128394 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "fff7f8c170ef477eabc03bb51111e63f",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Map: 0%| | 0/3668 [00:003\u001b[0m train_dataloader \u001b[39m=\u001b[39m DataLoader(tokenized_datasets[\u001b[39m'\u001b[39m\u001b[39mtrain\u001b[39m\u001b[39m'\u001b[39m],\n\u001b[0;32m 4\u001b[0m batch_size\u001b[39m=\u001b[39m\u001b[39m16\u001b[39m,\n\u001b[0;32m 5\u001b[0m shuffle\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m)\n\u001b[0;32m 7\u001b[0m \u001b[39mfor\u001b[39;00m step, batch \u001b[39min\u001b[39;00m \u001b[39menumerate\u001b[39m(train_dataloader):\n\u001b[1;32m----> 8\u001b[0m \u001b[39mprint\u001b[39m(batch[\u001b[39m'\u001b[39;49m\u001b[39minput_ids\u001b[39;49m\u001b[39m'\u001b[39;49m]\u001b[39m.\u001b[39;49mshape)\n\u001b[0;32m 9\u001b[0m \u001b[39mif\u001b[39;00m step\u001b[39m>\u001b[39m\u001b[39m5\u001b[39m:\n\u001b[0;32m 10\u001b[0m \u001b[39mbreak\u001b[39;00m\n",
+ "\u001b[1;31mAttributeError\u001b[0m: 'list' object has no attribute 'shape'"
+ ]
+ }
+ ],
+ "source": [
+ "from torch.utils.data import DataLoader\n",
+ "\n",
+ "train_dataloader = DataLoader(tokenized_datasets['train'],\n",
+ " batch_size=16,\n",
+ " shuffle=True)\n",
+ "\n",
+ "for step, batch in enumerate(train_dataloader):\n",
+ " print(batch['input_ids'].shape)\n",
+ " if step>5:\n",
+ " break"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'As you can see, the input_ids are a list at the moment and so we\\nare facing this issue. we need to convert this into a tensor!'"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "'''As you can see, the input_ids are a list at the moment and so we\n",
+ "are facing this issue. we need to convert this into a tensor!'''"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "tokenized_datasets = raw_datasets.map(tokenize_function, batched=True)\n",
+ "tokenized_datasets = tokenized_datasets.remove_columns(['idx','sentence1','sentence2'])\n",
+ "tokenized_datasets = tokenized_datasets.rename_column('label','labels')\n",
+ "tokenized_datasets = tokenized_datasets.with_format('pytorch')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'Now that you changed the format to pytorch, you will be able to input \\nthis tokenized dataset into the dataloader!'"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "'''Now that you changed the format to pytorch, you will be able to input \n",
+ "this tokenized dataset into the dataloader!'''"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "torch.Size([16, 128])\n",
+ "torch.Size([16, 128])\n",
+ "torch.Size([16, 128])\n",
+ "torch.Size([16, 128])\n",
+ "torch.Size([16, 128])\n",
+ "torch.Size([16, 128])\n",
+ "torch.Size([16, 128])\n"
+ ]
+ }
+ ],
+ "source": [
+ "from torch.utils.data import DataLoader\n",
+ "\n",
+ "train_dataloader = DataLoader(tokenized_datasets['train'], \n",
+ " batch_size=16,\n",
+ " shuffle=True)\n",
+ "\n",
+ "for step, batch in enumerate(train_dataloader):\n",
+ " print(batch['input_ids'].shape)\n",
+ " if step>5:\n",
+ " break"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Dynamic Padding"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'To apply dynamic padding:\\nwe must refer the part to the batch preperation!\\nSo we remove that part of padding from our tokenize function\\nbut leave the truncation part to True'"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "'''To apply dynamic padding:\n",
+ "we must refer the part to the batch preperation!\n",
+ "So we remove that part of padding from our tokenize function\n",
+ "but leave the truncation part to True'''"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "7591fbc9685244a48d641fb7501254d8",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Map: 0%| | 0/408 [00:005:\n",
+ " break"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "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": "3.11.6"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}