yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-06-26 23:50:03 +00:00
Code Issues Packages Projects Releases Wiki Activity
LLMs-from-scratch/appendix-E/01_main-chapter-code/appendix-E.ipynb
Sebastian Raschka c21bfe4a23
Add PyPI package (#576) 
* Add PyPI package

* fixes

* fixes
2025-03-23 19:28:49 -05:00

1553 lines
82 KiB
Plaintext
Raw Permalink Blame History

{
"cells": [
{
"cell_type": "markdown",
"id": "c024bfa4-1a7a-4751-b5a1-827225a3478b",
"metadata": {
"id": "c024bfa4-1a7a-4751-b5a1-827225a3478b"
},
"source": [
"<table style=\"width:100%\">\n",
"<tr>\n",
"<td style=\"vertical-align:middle; text-align:left;\">\n",
"<font size=\"2\">\n",
"Supplementary code for the <a href=\"http://mng.bz/orYv\">Build a Large Language Model From Scratch</a> book by <a href=\"https://sebastianraschka.com\">Sebastian Raschka</a><br>\n",
"<br>Code repository: <a href=\"https://github.com/rasbt/LLMs-from-scratch\">https://github.com/rasbt/LLMs-from-scratch</a>\n",
"</font>\n",
"</td>\n",
"<td style=\"vertical-align:middle; text-align:left;\">\n",
"<a href=\"http://mng.bz/orYv\"><img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/cover-small.webp\" width=\"100px\"></a>\n",
"</td>\n",
"</tr>\n",
"</table>\n"
]
},
{
"cell_type": "markdown",
"id": "58b8c870-fb72-490e-8916-d8129bd5d1ff",
"metadata": {
"id": "58b8c870-fb72-490e-8916-d8129bd5d1ff"
},
"source": [
"# Appendix E: Parameter-efficient Finetuning with LoRA"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "5b7e01c2-1c84-4f2a-bb51-2e0b74abda90",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "5b7e01c2-1c84-4f2a-bb51-2e0b74abda90",
"outputId": "316166b4-027a-4756-e9b4-fe88ae75dd4f"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"matplotlib version: 3.10.0\n",
"numpy version: 2.0.2\n",
"tiktoken version: 0.9.0\n",
"torch version: 2.6.0\n",
"tensorflow version: 2.18.0\n",
"pandas version: 2.2.3\n"
]
}
],
"source": [
"from importlib.metadata import version\n",
"\n",
"pkgs = [\"matplotlib\",\n",
" \"numpy\",\n",
" \"tiktoken\",\n",
" \"torch\",\n",
" \"tensorflow\", # For OpenAI's pretrained weights\n",
" \"pandas\" # Dataset loading\n",
" ]\n",
"for p in pkgs:\n",
" print(f\"{p} version: {version(p)}\")"
]
},
{
"cell_type": "markdown",
"id": "21532056-0ef4-4c98-82c7-e91f61c6485e",
"metadata": {
"id": "21532056-0ef4-4c98-82c7-e91f61c6485e"
},
"source": [
"## E.1 Introduction to LoRA"
]
},
{
"cell_type": "markdown",
"id": "66edc999-3d91-4a1c-a157-9d056392e8d8",
"metadata": {
"id": "66edc999-3d91-4a1c-a157-9d056392e8d8"
},
"source": [
"- No code in this section\n",
"- Low-rank adaptation (LoRA) is a machine learning technique that modifies a pretrained model to better suit a specific, often smaller, dataset by adjusting only a small, low-rank subset of the model's parameters\n",
"- This approach is important because it allows for efficient finetuning of large models on task-specific data, significantly reducing the computational cost and time required for finetuning"
]
},
{
"cell_type": "markdown",
"id": "5bb75b5d-d59c-4948-821a-1594a5883dc1",
"metadata": {
"id": "5bb75b5d-d59c-4948-821a-1594a5883dc1"
},
"source": [
"- Suppose we have a large weight matrix $W$ for a given layer\n",
"- During backpropagation, we learn a $\\Delta W$ matrix, which contains information on how much we want to update the original weights to minimize the loss function during training\n",
"- In regular training and finetuning, the weight update is defined as follows:\n",
"\n",
"$$W_{\\text{updated}} = W + \\Delta W$$\n",
"\n",
"- The LoRA method proposed by [Hu et al.](https://arxiv.org/abs/2106.09685) offers a more efficient alternative to computing the weight updates $\\Delta W$ by learning an approximation of it, $\\Delta W \\approx AB$.\n",
"- In other words, in LoRA, we have the following, where $A$ and $B$ are two small weight matrices:\n",
"\n",
"$$W_{\\text{updated}} = W + AB$$\n",
"\n",
"- The figure below illustrates these formulas for full finetuning and LoRA side by side"
]
},
{
"cell_type": "markdown",
"id": "a8a7419d-cae9-4525-bb44-1641f6ef4f3b",
"metadata": {
"id": "a8a7419d-cae9-4525-bb44-1641f6ef4f3b"
},
"source": [
"<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-e_compressed/lora-1.webp\" width=\"500px\">"
]
},
{
"cell_type": "markdown",
"id": "4edd43c9-8ec5-48e6-b3fc-5fb3c16037cc",
"metadata": {
"id": "4edd43c9-8ec5-48e6-b3fc-5fb3c16037cc"
},
"source": [
"- If you paid close attention, the full finetuning and LoRA depictions in the figure above look slightly different from the formulas I have shown earlier\n",
"- That's due to the distributive law of matrix multiplication: we don't have to add the weights with the updated weights but can keep them separate\n",
"- For instance, if $x$ is the input data, then we can write the following for regular finetuning:\n",
"\n",
"$$x (W+\\Delta W) = x W + x \\Delta W$$\n",
"\n",
"- Similarly, we can write the following for LoRA:\n",
"\n",
"$$x (W+A B) = x W + x A B$$\n",
"\n",
"- The fact that we can keep the LoRA weight matrices separate makes LoRA especially attractive\n",
"- In practice, this means that we don't have to modify the weights of the pretrained model at all, as we can apply the LoRA matrices on the fly\n",
"- After setting up the dataset and loading the model, we will implement LoRA in the code to make these concepts less abstract"
]
},
{
"cell_type": "markdown",
"id": "8c7017a2-32aa-4002-a2f3-12aac293ccdf",
"metadata": {
"id": "8c7017a2-32aa-4002-a2f3-12aac293ccdf"
},
"source": [
"## E.2 Preparing the dataset"
]
},
{
"cell_type": "markdown",
"id": "669c64df-4431-4d27-834d-2bb38a01fc02",
"metadata": {
"id": "669c64df-4431-4d27-834d-2bb38a01fc02"
},
"source": [
"- This section repeats the code from chapter 6 to load and prepare the dataset\n",
"- Instead of repeating this code, one could open and run the chapter 6 notebook and then insert the LoRA code from section E.4 there\n",
"- (The LoRA code was originally the last section of chapter 6 but was moved to the appendix due to the length of chapter 6)\n",
"- In a similar fashion, we could also apply LoRA to the models in chapter 7 for instruction finetuning"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "def7c09b-af9c-4216-90ce-5e67aed1065c",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "def7c09b-af9c-4216-90ce-5e67aed1065c",
"outputId": "a67a7afe-b401-4463-c731-87025d20f72d"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File downloaded and saved as sms_spam_collection/SMSSpamCollection.tsv\n"
]
}
],
"source": [
"import urllib\n",
"from pathlib import Path\n",
"import pandas as pd\n",
"from previous_chapters import (\n",
" download_and_unzip_spam_data,\n",
" create_balanced_dataset,\n",
" random_split\n",
")\n",
"# If the `previous_chapters.py` file is not available locally,\n",
"# you can import it from the `llms-from-scratch` PyPI package.\n",
"# For details, see: https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg\n",
"# E.g.,\n",
"# from llms_from_scratch.ch06 import (\n",
"# download_and_unzip_spam_data,\n",
"# create_balanced_dataset,\n",
"# random_split\n",
"# )\n",
"\n",
"\n",
"\n",
"url = \"https://archive.ics.uci.edu/static/public/228/sms+spam+collection.zip\"\n",
"zip_path = \"sms_spam_collection.zip\"\n",
"extracted_path = \"sms_spam_collection\"\n",
"data_file_path = Path(extracted_path) / \"SMSSpamCollection.tsv\"\n",
"\n",
"try:\n",
" download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n",
"except (urllib.error.HTTPError, urllib.error.URLError, TimeoutError) as e:\n",
" print(f\"Primary URL failed: {e}. Trying backup URL...\")\n",
" url = \"https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip\"\n",
" download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)\n",
"\n",
"df = pd.read_csv(data_file_path, sep=\"\\t\", header=None, names=[\"Label\", \"Text\"])\n",
"balanced_df = create_balanced_dataset(df)\n",
"balanced_df[\"Label\"] = balanced_df[\"Label\"].map({\"ham\": 0, \"spam\": 1})\n",
"\n",
"train_df, validation_df, test_df = random_split(balanced_df, 0.7, 0.1)\n",
"train_df.to_csv(\"train.csv\", index=None)\n",
"validation_df.to_csv(\"validation.csv\", index=None)\n",
"test_df.to_csv(\"test.csv\", index=None)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "74c3c463-8763-4cc0-9320-41c7eaad8ab7",
"metadata": {
"id": "74c3c463-8763-4cc0-9320-41c7eaad8ab7"
},
"outputs": [],
"source": [
"import torch\n",
"import tiktoken\n",
"from previous_chapters import SpamDataset\n",
"\n",
"\n",
"tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
"train_dataset = SpamDataset(\"train.csv\", max_length=None, tokenizer=tokenizer)\n",
"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)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "8681adc0-6f02-4e75-b01a-a6ab75d05542",
"metadata": {
"id": "8681adc0-6f02-4e75-b01a-a6ab75d05542"
},
"outputs": [],
"source": [
"from torch.utils.data import DataLoader\n",
"\n",
"num_workers = 0\n",
"batch_size = 8\n",
"\n",
"torch.manual_seed(123)\n",
"\n",
"train_loader = DataLoader(\n",
" dataset=train_dataset,\n",
" batch_size=batch_size,\n",
" shuffle=True,\n",
" num_workers=num_workers,\n",
" drop_last=True,\n",
")\n",
"\n",
"val_loader = DataLoader(\n",
" dataset=val_dataset,\n",
" batch_size=batch_size,\n",
" num_workers=num_workers,\n",
" drop_last=False,\n",
")\n",
"\n",
"test_loader = DataLoader(\n",
" dataset=test_dataset,\n",
" batch_size=batch_size,\n",
" num_workers=num_workers,\n",
" drop_last=False,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "ab7335db-e0bb-4e27-80c5-eea11e593a57",
"metadata": {
"id": "ab7335db-e0bb-4e27-80c5-eea11e593a57"
},
"source": [
"- As a verification step, we iterate through the data loaders and check that the batches contain 8 training examples each, where each training example consists of 120 tokens"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4dee6882-4c3a-4964-af15-fa31f86ad047",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "4dee6882-4c3a-4964-af15-fa31f86ad047",
"outputId": "2ae34de1-dd01-4f99-d2c8-ba4dca400754"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train loader:\n",
"Input batch dimensions: torch.Size([8, 120])\n",
"Label batch dimensions torch.Size([8])\n"
]
}
],
"source": [
"print(\"Train loader:\")\n",
"for input_batch, target_batch in train_loader:\n",
" pass\n",
"\n",
"print(\"Input batch dimensions:\", input_batch.shape)\n",
"print(\"Label batch dimensions\", target_batch.shape)"
]
},
{
"cell_type": "markdown",
"id": "5cdd7947-7039-49bf-8a5e-c0a2f4281ca1",
"metadata": {
"id": "5cdd7947-7039-49bf-8a5e-c0a2f4281ca1"
},
"source": [
"- Lastly, let's print the total number of batches in each dataset"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "IZfw-TYD2zTj",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "IZfw-TYD2zTj",
"outputId": "4d19ed61-cf7a-4ec4-b822-c847dd1c5d77"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"130 training batches\n",
"19 validation batches\n",
"38 test batches\n"
]
}
],
"source": [
"print(f\"{len(train_loader)} training batches\")\n",
"print(f\"{len(val_loader)} validation batches\")\n",
"print(f\"{len(test_loader)} test batches\")"
]
},
{
"cell_type": "markdown",
"id": "dec9aa4a-ffd2-4d9f-a835-cce1059fe604",
"metadata": {
"id": "dec9aa4a-ffd2-4d9f-a835-cce1059fe604"
},
"source": [
"## E.3 Initializing the model"
]
},
{
"cell_type": "markdown",
"id": "f36ebdaf-810e-46a2-9ad9-e017a04051b1",
"metadata": {
"id": "f36ebdaf-810e-46a2-9ad9-e017a04051b1"
},
"source": [
"- This section repeats the code from chapter 6 to load and prepare the model"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "02b3a506-3879-4258-82b5-93a5b6bafa74",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "02b3a506-3879-4258-82b5-93a5b6bafa74",
"outputId": "b8c9b125-bb52-45d3-8071-fa5054dbf5a9"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"checkpoint: 100%|███████████████████████████| 77.0/77.0 [00:00<00:00, 45.0kiB/s]\n",
"encoder.json: 100%|███████████████████████| 1.04M/1.04M [00:00<00:00, 2.15MiB/s]\n",
"hparams.json: 100%|█████████████████████████| 90.0/90.0 [00:00<00:00, 54.5kiB/s]\n",
"model.ckpt.data-00000-of-00001: 100%|███████| 498M/498M [01:12<00:00, 6.86MiB/s]\n",
"model.ckpt.index: 100%|███████████████████| 5.21k/5.21k [00:00<00:00, 2.99MiB/s]\n",
"model.ckpt.meta: 100%|██████████████████████| 471k/471k [00:00<00:00, 1.32MiB/s]\n",
"vocab.bpe: 100%|████████████████████████████| 456k/456k [00:00<00:00, 1.48MiB/s]\n"
]
}
],
"source": [
"from gpt_download import download_and_load_gpt2\n",
"from previous_chapters import GPTModel, load_weights_into_gpt\n",
"# Alternatively:\n",
"# from llms_from_scratch.ch04 import GPTModel\n",
"# from llms_from_scratch.ch05 import load_weights_into_gpt\n",
"\n",
"\n",
"\n",
"CHOOSE_MODEL = \"gpt2-small (124M)\"\n",
"INPUT_PROMPT = \"Every effort moves\"\n",
"\n",
"BASE_CONFIG = {\n",
" \"vocab_size\": 50257, # Vocabulary size\n",
" \"context_length\": 1024, # Context length\n",
" \"drop_rate\": 0.0, # Dropout rate\n",
" \"qkv_bias\": True # Query-key-value bias\n",
"}\n",
"\n",
"model_configs = {\n",
" \"gpt2-small (124M)\": {\"emb_dim\": 768, \"n_layers\": 12, \"n_heads\": 12},\n",
" \"gpt2-medium (355M)\": {\"emb_dim\": 1024, \"n_layers\": 24, \"n_heads\": 16},\n",
" \"gpt2-large (774M)\": {\"emb_dim\": 1280, \"n_layers\": 36, \"n_heads\": 20},\n",
" \"gpt2-xl (1558M)\": {\"emb_dim\": 1600, \"n_layers\": 48, \"n_heads\": 25},\n",
"}\n",
"\n",
"BASE_CONFIG.update(model_configs[CHOOSE_MODEL])\n",
"\n",
"model_size = CHOOSE_MODEL.split(\" \")[-1].lstrip(\"(\").rstrip(\")\")\n",
"settings, params = download_and_load_gpt2(model_size=model_size, models_dir=\"gpt2\")\n",
"\n",
"model = GPTModel(BASE_CONFIG)\n",
"load_weights_into_gpt(model, params)\n",
"model.eval();"
]
},
{
"cell_type": "markdown",
"id": "252614cd-7ce6-4908-83e6-3761f519904e",
"metadata": {
"id": "252614cd-7ce6-4908-83e6-3761f519904e"
},
"source": [
"- To ensure that the model was loaded corrected, let's double-check that it generates coherent text"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "8b6ce20c-0700-4783-8be0-4cf17c200a7f",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "8b6ce20c-0700-4783-8be0-4cf17c200a7f",
"outputId": "28ccbca5-8de9-41a0-c093-da00fcbaa91c"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Every effort moves you forward.\n",
"\n",
"The first step is to understand the importance of your work\n"
]
}
],
"source": [
"from previous_chapters import (\n",
" generate_text_simple,\n",
" text_to_token_ids,\n",
" token_ids_to_text\n",
")\n",
"\n",
"\n",
"text_1 = \"Every effort moves you\"\n",
"\n",
"token_ids = generate_text_simple(\n",
" model=model,\n",
" idx=text_to_token_ids(text_1, tokenizer),\n",
" max_new_tokens=15,\n",
" context_size=BASE_CONFIG[\"context_length\"]\n",
")\n",
"\n",
"print(token_ids_to_text(token_ids, tokenizer))"
]
},
{
"cell_type": "markdown",
"id": "8174b31b-1ab5-4115-b01c-245369da5af3",
"metadata": {
"id": "8174b31b-1ab5-4115-b01c-245369da5af3"
},
"source": [
"- Then, we prepare the model for classification finetuning similar to chapter 6, where we replace the output layer"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "e255ce91-d73a-4854-90a4-95804928eb16",
"metadata": {
"id": "e255ce91-d73a-4854-90a4-95804928eb16"
},
"outputs": [],
"source": [
"torch.manual_seed(123)\n",
"\n",
"num_classes = 2\n",
"model.out_head = torch.nn.Linear(in_features=768, out_features=num_classes)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "02e6f057-1383-4ece-8444-0a88e71ac75d",
"metadata": {
"id": "02e6f057-1383-4ece-8444-0a88e71ac75d"
},
"outputs": [],
"source": [
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"\n",
"# Note:\n",
"# Uncommenting the following lines will allow the code to run on Apple Silicon chips, if applicable,\n",
"# which is approximately 1.2x faster than on an Apple CPU (as measured on an M3 MacBook Air).\n",
"# However, the resulting loss values may be slightly different.\n",
"\n",
"#if torch.cuda.is_available():\n",
"# device = torch.device(\"cuda\")\n",
"#elif torch.backends.mps.is_available():\n",
"# device = torch.device(\"mps\")\n",
"#else:\n",
"# device = torch.device(\"cpu\")\n",
"#\n",
"# print(f\"Using {device} device.\")\n",
"\n",
"model.to(device); # no assignment model = model.to(device) necessary for nn.Module classes"
]
},
{
"cell_type": "markdown",
"id": "8e951cd6-5e42-44d2-b21f-895cb61004fe",
"metadata": {
"id": "8e951cd6-5e42-44d2-b21f-895cb61004fe"
},
"source": [
"- Lastly, let's calculate the initial classification accuracy of the non-finetuned model (we expect this to be around 50%, which means that the model is not able to distinguish between spam and non-spam messages yet reliably)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "fc7dd72c-73a2-4881-ade0-0a9605f1ab8c",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "fc7dd72c-73a2-4881-ade0-0a9605f1ab8c",
"outputId": "74848515-5a49-4125-fecb-9f4bac23f812"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Training accuracy: 46.25%\n",
"Validation accuracy: 45.00%\n",
"Test accuracy: 48.75%\n"
]
}
],
"source": [
"from previous_chapters import calc_accuracy_loader\n",
"# Alternatively:\n",
"# from llms_from_scratch.ch06 import calc_accuracy_loader\n",
"\n",
"\n",
"\n",
"torch.manual_seed(123)\n",
"train_accuracy = calc_accuracy_loader(train_loader, model, device, num_batches=10)\n",
"val_accuracy = calc_accuracy_loader(val_loader, model, device, num_batches=10)\n",
"test_accuracy = calc_accuracy_loader(test_loader, model, device, num_batches=10)\n",
"\n",
"print(f\"Training accuracy: {train_accuracy*100:.2f}%\")\n",
"print(f\"Validation accuracy: {val_accuracy*100:.2f}%\")\n",
"print(f\"Test accuracy: {test_accuracy*100:.2f}%\")"
]
},
{
"cell_type": "markdown",
"id": "398a1ec9-e2a1-43d6-bf9f-12ee54b46a7b",
"metadata": {
"id": "398a1ec9-e2a1-43d6-bf9f-12ee54b46a7b"
},
"source": [
"## E.4 Parameter-efficient finetuning with LoRA"
]
},
{
"cell_type": "markdown",
"id": "652a4a82-61ef-4d0a-9858-8988e844f12c",
"metadata": {
"id": "652a4a82-61ef-4d0a-9858-8988e844f12c"
},
"source": [
"- We begin by initializing a LoRALayer that creates the matrices $A$ and $B$, along with the `alpha` scaling hyperparameter and the `rank` ($r$) hyperparameters\n",
"- This layer can accept an input and compute the corresponding output, as illustrated in the figure below\n",
"\n",
"<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-e_compressed/lora-2.webp\" width=\"200px\">\n",
"\n",
"In code, this LoRA layer depicted in the figure above looks like as follows"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "2ds9ywjMwvIW",
"metadata": {
"id": "2ds9ywjMwvIW"
},
"outputs": [],
"source": [
"import math\n",
"\n",
"class LoRALayer(torch.nn.Module):\n",
" def __init__(self, in_dim, out_dim, rank, alpha):\n",
" super().__init__()\n",
" self.A = torch.nn.Parameter(torch.empty(in_dim, rank))\n",
" torch.nn.init.kaiming_uniform_(self.A, a=math.sqrt(5)) # similar to standard weight initialization\n",
" self.B = torch.nn.Parameter(torch.zeros(rank, out_dim))\n",
" self.alpha = alpha\n",
"\n",
" def forward(self, x):\n",
" x = self.alpha * (x @ self.A @ self.B)\n",
" return x"
]
},
{
"cell_type": "markdown",
"id": "ad21faa8-0614-4257-93cd-68952193e14a",
"metadata": {
"id": "ad21faa8-0614-4257-93cd-68952193e14a"
},
"source": [
"- In the code above, `rank` is a hyperparameter that controls the inner dimension of the matrices $A$ and $B$\n",
"- In other words, this parameter controls the number of additional parameters introduced by LoRA and is a key factor in determining the balance between model adaptability and parameter efficiency\n",
"- The second hyperparameter, `alpha`, is a scaling hyperparameter applied to the output of the low-rank adaptation\n",
"- It essentially controls the extent to which the adapted layer's output is allowed to influence the original output of the layer being adapted\n",
"- This can be seen as a way to regulate the impact of the low-rank adaptation on the layer's output\n",
"- So far, the `LoRALayer` class we implemented above allows us to transform the layer inputs $x$\n",
"- However, in LoRA, we are usually interested in replacing existing `Linear` layers so that the weight update is applied to the existing pretrained weights, as shown in the figure below\n",
"\n",
"<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-e_compressed/lora-3.webp\" width=\"200px\">"
]
},
{
"cell_type": "markdown",
"id": "3e6d5da0-dfce-4808-b89b-29ff333f563f",
"metadata": {
"id": "3e6d5da0-dfce-4808-b89b-29ff333f563f"
},
"source": [
"- To incorporate the original `Linear` layer weights as shown in the figure above, we implement a `LinearWithLoRA` layer below that uses the previously implemented LoRALayer and can be used to replace existing `Linear` layers in a neural network, for example, the self-attention module or feed forward modules in an LLM"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "127d3a64-8359-4b21-b056-78d58cc75fe8",
"metadata": {
"id": "127d3a64-8359-4b21-b056-78d58cc75fe8"
},
"outputs": [],
"source": [
"class LinearWithLoRA(torch.nn.Module):\n",
" def __init__(self, linear, rank, alpha):\n",
" super().__init__()\n",
" self.linear = linear\n",
" self.lora = LoRALayer(\n",
" linear.in_features, linear.out_features, rank, alpha\n",
" )\n",
"\n",
" def forward(self, x):\n",
" return self.linear(x) + self.lora(x)"
]
},
{
"cell_type": "markdown",
"id": "e1145a90-35ff-462c-820b-15483fa5b051",
"metadata": {
"id": "e1145a90-35ff-462c-820b-15483fa5b051"
},
"source": [
"- Note that since we initialize the weight matrix $B$ (`self.B` in `LoRALayer`) with zero values in the LoRA layer, the matrix multiplication between $A$ and $B$ results in a matrix consisting of 0's and doesn't affect the original weights (since adding 0 to the original weights does not modify them)"
]
},
{
"cell_type": "markdown",
"id": "e98a6d36-7bc9-434c-a7f1-533f26aff06d",
"metadata": {
"id": "e98a6d36-7bc9-434c-a7f1-533f26aff06d"
},
"source": [
"- To try LoRA on the GPT model we defined earlier, we define a `replace_linear_with_lora` function to replace all `Linear` layers in the model with the new `LinearWithLoRA` layers\n",
"\n",
"<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-e_compressed/lora-4.webp\" width=\"400px\">"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "WlQZ8ygqzN_g",
"metadata": {
"id": "WlQZ8ygqzN_g"
},
"outputs": [],
"source": [
"def replace_linear_with_lora(model, rank, alpha):\n",
" for name, module in model.named_children():\n",
" if isinstance(module, torch.nn.Linear):\n",
" # Replace the Linear layer with LinearWithLoRA\n",
" setattr(model, name, LinearWithLoRA(module, rank, alpha))\n",
" else:\n",
" # Recursively apply the same function to child modules\n",
" replace_linear_with_lora(module, rank, alpha)"
]
},
{
"cell_type": "markdown",
"id": "8c172164-cdde-4489-b7d7-aaed9cc2f5f2",
"metadata": {
"id": "8c172164-cdde-4489-b7d7-aaed9cc2f5f2"
},
"source": [
"- We then freeze the original model parameter and use the `replace_linear_with_lora` to replace the said `Linear` layers using the code below\n",
"- This will replace the `Linear` layers in the LLM with `LinearWithLoRA` layers"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "dbe15350-4da9-4829-9d23-98bbd3d0b1a1",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "dbe15350-4da9-4829-9d23-98bbd3d0b1a1",
"outputId": "fd4c208f-854a-4701-d9d3-9d73af733364"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total trainable parameters before: 124,441,346\n",
"Total trainable parameters after: 0\n"
]
}
],
"source": [
"total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)\n",
"print(f\"Total trainable parameters before: {total_params:,}\")\n",
"\n",
"for param in model.parameters():\n",
" param.requires_grad = False\n",
"\n",
"total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)\n",
"print(f\"Total trainable parameters after: {total_params:,}\")"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "mLk_fPq0yz_u",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "mLk_fPq0yz_u",
"outputId": "0a93b8fc-05d7-4ace-ee47-e2fc6bdd7d75"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total trainable LoRA parameters: 2,666,528\n"
]
}
],
"source": [
"replace_linear_with_lora(model, rank=16, alpha=16)\n",
"\n",
"total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)\n",
"print(f\"Total trainable LoRA parameters: {total_params:,}\")"
]
},
{
"cell_type": "markdown",
"id": "b8b6819e-ef7a-4f0d-841a-1b467496bef9",
"metadata": {
"id": "b8b6819e-ef7a-4f0d-841a-1b467496bef9"
},
"source": [
"- As we can see, we reduced the number of trainable parameters by almost 50x when using LoRA\n",
"- Let's now double-check whether the layers have been modified as intended by printing the model architecture"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "1711be61-bb2c-466f-9b5b-24f4aa5ccd9c",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "1711be61-bb2c-466f-9b5b-24f4aa5ccd9c",
"outputId": "acff8eca-3775-45a2-b62d-032a986ef037"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"GPTModel(\n",
" (tok_emb): Embedding(50257, 768)\n",
" (pos_emb): Embedding(1024, 768)\n",
" (drop_emb): Dropout(p=0.0, inplace=False)\n",
" (trf_blocks): Sequential(\n",
" (0): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (1): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (2): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (3): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (4): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (5): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (6): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (7): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (8): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (9): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (10): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (11): TransformerBlock(\n",
" (att): MultiHeadAttention(\n",
" (W_query): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_key): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (W_value): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (out_proj): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (dropout): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ff): FeedForward(\n",
" (layers): Sequential(\n",
" (0): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=3072, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" (1): GELU()\n",
" (2): LinearWithLoRA(\n",
" (linear): Linear(in_features=3072, out_features=768, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
" )\n",
" )\n",
" (norm1): LayerNorm()\n",
" (norm2): LayerNorm()\n",
" (drop_resid): Dropout(p=0.0, inplace=False)\n",
" )\n",
" )\n",
" (final_norm): LayerNorm()\n",
" (out_head): LinearWithLoRA(\n",
" (linear): Linear(in_features=768, out_features=2, bias=True)\n",
" (lora): LoRALayer()\n",
" )\n",
")\n"
]
}
],
"source": [
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"model.to(device)\n",
"\n",
"print(model)"
]
},
{
"cell_type": "markdown",
"id": "c4bbc9d7-65ec-4675-bab8-2e56eb0cfb55",
"metadata": {
"id": "c4bbc9d7-65ec-4675-bab8-2e56eb0cfb55"
},
"source": [
"- Based on the model architecture above, we can see that the model now contains our new `LinearWithLoRA` layers\n",
"- Also, since we initialized matrix $B$ with 0's, we expect the initial model performance to be unchanged compared to before"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "DAlrb_I00VEU",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "DAlrb_I00VEU",
"outputId": "3da44ac4-230b-4358-d996-30b63f0d962a"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Training accuracy: 46.25%\n",
"Validation accuracy: 45.00%\n",
"Test accuracy: 48.75%\n"
]
}
],
"source": [
"torch.manual_seed(123)\n",
"train_accuracy = calc_accuracy_loader(train_loader, model, device, num_batches=10)\n",
"val_accuracy = calc_accuracy_loader(val_loader, model, device, num_batches=10)\n",
"test_accuracy = calc_accuracy_loader(test_loader, model, device, num_batches=10)\n",
"\n",
"print(f\"Training accuracy: {train_accuracy*100:.2f}%\")\n",
"print(f\"Validation accuracy: {val_accuracy*100:.2f}%\")\n",
"print(f\"Test accuracy: {test_accuracy*100:.2f}%\")"
]
},
{
"cell_type": "markdown",
"id": "13735b3e-f0c3-4dba-ae3d-4141b2878101",
"metadata": {
"id": "13735b3e-f0c3-4dba-ae3d-4141b2878101"
},
"source": [
"- Let's now get to the interesting part and finetune the model by reusing the training function from chapter 6\n",
"- The training takes about 15 minutes on a M3 MacBook Air laptop computer and less than half a minute on a V100 or A100 GPU"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "wCParRvr0eff",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "wCParRvr0eff",
"outputId": "ce910a9c-ee89-48bb-bfa6-49c6aee1e450"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Ep 1 (Step 000000): Train loss 3.820, Val loss 3.462\n",
"Ep 1 (Step 000050): Train loss 0.396, Val loss 0.364\n",
"Ep 1 (Step 000100): Train loss 0.111, Val loss 0.229\n",
"Training accuracy: 97.50% | Validation accuracy: 95.00%\n",
"Ep 2 (Step 000150): Train loss 0.135, Val loss 0.073\n",
"Ep 2 (Step 000200): Train loss 0.008, Val loss 0.052\n",
"Ep 2 (Step 000250): Train loss 0.021, Val loss 0.179\n",
"Training accuracy: 97.50% | Validation accuracy: 97.50%\n",
"Ep 3 (Step 000300): Train loss 0.096, Val loss 0.080\n",
"Ep 3 (Step 000350): Train loss 0.010, Val loss 0.116\n",
"Training accuracy: 97.50% | Validation accuracy: 95.00%\n",
"Ep 4 (Step 000400): Train loss 0.003, Val loss 0.151\n",
"Ep 4 (Step 000450): Train loss 0.008, Val loss 0.077\n",
"Ep 4 (Step 000500): Train loss 0.001, Val loss 0.147\n",
"Training accuracy: 100.00% | Validation accuracy: 97.50%\n",
"Ep 5 (Step 000550): Train loss 0.007, Val loss 0.094\n",
"Ep 5 (Step 000600): Train loss 0.000, Val loss 0.056\n",
"Training accuracy: 100.00% | Validation accuracy: 97.50%\n",
"Training completed in 12.10 minutes.\n"
]
}
],
"source": [
"import time\n",
"from previous_chapters import train_classifier_simple\n",
"# Alternatively:\n",
"# from llms_from_scratch.ch06 import train_classifier_simple\n",
"\n",
"\n",
"start_time = time.time()\n",
"\n",
"torch.manual_seed(123)\n",
"\n",
"optimizer = torch.optim.AdamW(model.parameters(), lr=5e-5, weight_decay=0.1)\n",
"\n",
"num_epochs = 5\n",
"train_losses, val_losses, train_accs, val_accs, examples_seen = train_classifier_simple(\n",
" model, train_loader, val_loader, optimizer, device,\n",
" num_epochs=num_epochs, eval_freq=50, eval_iter=5,\n",
")\n",
"\n",
"end_time = time.time()\n",
"execution_time_minutes = (end_time - start_time) / 60\n",
"print(f\"Training completed in {execution_time_minutes:.2f} minutes.\")"
]
},
{
"cell_type": "markdown",
"id": "d0c89e82-3aa8-44c6-b046-0b16200b8e6c",
"metadata": {
"id": "d0c89e82-3aa8-44c6-b046-0b16200b8e6c"
},
"source": [
"- Finally, let's evaluate the model"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "bawWGijA0iF3",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 308
},
"id": "bawWGijA0iF3",
"outputId": "af70782a-d605-4376-fa6c-d33b38979cfa"
},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 500x300 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from previous_chapters import plot_values\n",
"# Alternatively:\n",
"# from llms_from_scratch.ch06 import plot_values\n",
"\n",
"epochs_tensor = torch.linspace(0, num_epochs, len(train_losses))\n",
"examples_seen_tensor = torch.linspace(0, examples_seen, len(train_losses))\n",
"\n",
"plot_values(epochs_tensor, examples_seen_tensor, train_losses, val_losses, label=\"loss\")"
]
},
{
"cell_type": "markdown",
"id": "aa074723-e3f7-4f7e-a267-855531a037dc",
"metadata": {
"id": "aa074723-e3f7-4f7e-a267-855531a037dc"
},
"source": [
"- Note that we previously calculated the accuracy values on 5 batches only via the `eval_iter=5` setting; below, we calculate the accuracies on the full dataset"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "1D2awlEq0gZi",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "1D2awlEq0gZi",
"outputId": "d603eda1-d912-43eb-ec9c-af6a622510a0"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Training accuracy: 100.00%\n",
"Validation accuracy: 96.64%\n",
"Test accuracy: 97.33%\n"
]
}
],
"source": [
"train_accuracy = calc_accuracy_loader(train_loader, model, device)\n",
"val_accuracy = calc_accuracy_loader(val_loader, model, device)\n",
"test_accuracy = calc_accuracy_loader(test_loader, model, device)\n",
"\n",
"print(f\"Training accuracy: {train_accuracy*100:.2f}%\")\n",
"print(f\"Validation accuracy: {val_accuracy*100:.2f}%\")\n",
"print(f\"Test accuracy: {test_accuracy*100:.2f}%\")"
]
},
{
"cell_type": "markdown",
"id": "1f87f5e6-339e-4fcf-900b-6d845d3c713d",
"metadata": {
"id": "1f87f5e6-339e-4fcf-900b-6d845d3c713d"
},
"source": [
"- As we can see based on the relatively high accuracy values above, the LoRA finetuning was successful"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "V100",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.10.16"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue View Git Blame Copy Permalink