Preprocessing data for fine-tuning

Fine-Tuning with Llama 3

Francesca Donadoni

Curriculum Manager, DataCamp

Using datasets for fine-tuning

  • Quality of the data is key

  • Training Set:

    • For model training
    • Majority of the data

Diagram of a dataset with a training sets.

Fine-Tuning with Llama 3

Using datasets for fine-tuning

  • Quality of the data is key

  • Training Set:

    • For model training
    • Majority of the data
  • Validation Set:
    • For selecting the best model version

Diagram of a training and validation set.

Fine-Tuning with Llama 3

Using datasets for fine-tuning

  • Quality of the data is key

  • Training Set:

    • For model training
    • Majority of the data
  • Validation Set:
    • For selecting the best model version
  • Test Set:
    • For evaluating model's performance

Diagram of a training, validation, and test set.

Fine-Tuning with Llama 3

Preparing data using the datasets library

 

  • Datasets library
  • Preprocessing
  • Split
  • Load
  • Manage memory

A diagram of the flow of data, from the dataset flowing into the datasets library, which shows 3 green boxes for preprocessing, loading/managing data, and integrations, followed with an arrow pointing to the output, which is a box showing prepared data.

Fine-Tuning with Llama 3

Loading a customer service dataset

from datasets import load_dataset

ds = load_dataset(
    'bitext/Bitext-customer-support-llm-chatbot-training-dataset',

    split="train"

)

print(ds.column_names)

['flags', 'instruction', 'category', 'intent', 'response']
Fine-Tuning with Llama 3

Peeking into the data

import pprint
pprint.pprint(ds[0])

{'category': 'ORDER',
 'flags': 'B',
 'instruction': 'question about cancelling order {{Order Number}}',
 'intent': 'cancel_order',
 'response': "I've understood you have a question regarding canceling order "
             "{{Order Number}}, and I'm here to provide you with the "
             'information you need. Please go ahead and ask your question, and '
             "I'll do my best to assist you."}
Fine-Tuning with Llama 3

Filtering the dataset

from datasets import load_dataset, Dataset

ds = load_dataset(
    'bitext/Bitext-customer-support-llm-chatbot-training-dataset',
    split="train")

print(ds.shape)

(26872, 5)

first_thousand_points = ds[:1000]

ds = Dataset.from_dict(first_thousand_points)
Fine-Tuning with Llama 3

Preprocessing the dataset

def merge_example(row):

    row['conversation'] = f"Query: {row['instruction']}\nResponse: {row['response']}"
    return row

ds = ds.map(merge_example)

print(ds[0]['conversation'])

Query: question about cancelling order {{Order Number}}
Response: I've understood you have a question regarding canceling order {{Order Number}}, 
and I'm here to provide you with the information you need. Please go ahead and ask your 
question, and I'll do my best to assist you.
Fine-Tuning with Llama 3

Saving the preprocessed dataset

ds.save_to_disk("preprocessed_dataset")

Saving the dataset (1/1 shards): 100%
26872/26872 [00:00<00:00, 383823.33 examples/s]

from datasets import load_from_disk
ds_preprocessed = load_from_disk("preprocessed_dataset")
Fine-Tuning with Llama 3

Using Hugging Face datasets with TorchTune

 

  • Can use Hugging Face dataset with TorchTune
  • Set a dataset path and configurations

 

tune run full_finetune_single_device --config llama3/8B_full_single_device \
dataset=preprocessed_dataset dataset.split=train
Fine-Tuning with Llama 3

Let's practice!

Fine-Tuning with Llama 3

Preparing Video For Download...