Code for How to Fine Tune BERT for Text Classification using Transformers in Python Tutorial


View on Github

Open in Colab

train.py

# !pip install transformers

import torch
from transformers.file_utils import is_tf_available, is_torch_available, is_torch_tpu_available
from transformers import BertTokenizerFast, BertForSequenceClassification
from transformers import Trainer, TrainingArguments
import numpy as np
import random
from sklearn.datasets import fetch_20newsgroups
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score


def set_seed(seed: int):
    """
    Helper function for reproducible behavior to set the seed in ``random``, ``numpy``, ``torch`` and/or ``tf`` (if
    installed).

    Args:
        seed (:obj:`int`): The seed to set.
    """
    random.seed(seed)
    np.random.seed(seed)
    if is_torch_available():
        torch.manual_seed(seed)
        torch.cuda.manual_seed_all(seed)
        # safe to call this function even if cuda is not available
    if is_tf_available():
        import tensorflow as tf
        tf.random.set_seed(seed)

set_seed(1)

# the model we gonna train, base uncased BERT
# check text classification models here: https://huggingface.co/models?filter=text-classification
model_name = "bert-base-uncased"
# max sequence length for each document/sentence sample
max_length = 512
# load the tokenizer
tokenizer = BertTokenizerFast.from_pretrained(model_name, do_lower_case=True)

def read_20newsgroups(test_size=0.2):
    # download & load 20newsgroups dataset from sklearn's repos
    dataset = fetch_20newsgroups(subset="all", shuffle=True, remove=("headers", "footers", "quotes"))
    documents = dataset.data
    labels = dataset.target
    # split into training & testing a return data as well as label names
    return train_test_split(documents, labels, test_size=test_size), dataset.target_names

# call the function
(train_texts, valid_texts, train_labels, valid_labels), target_names = read_20newsgroups()
# tokenize the dataset, truncate when passed `max_length`, 
# and pad with 0's when less than `max_length`
train_encodings = tokenizer(train_texts, truncation=True, padding=True, max_length=max_length)
valid_encodings = tokenizer(valid_texts, truncation=True, padding=True, max_length=max_length)

class NewsGroupsDataset(torch.utils.data.Dataset):
    def __init__(self, encodings, labels):
        self.encodings = encodings
        self.labels = labels

    def __getitem__(self, idx):
        item = {k: torch.tensor(v[idx]) for k, v in self.encodings.items()}
        item["labels"] = torch.tensor([self.labels[idx]])
        return item

    def __len__(self):
        return len(self.labels)

# convert our tokenized data into a torch Dataset
train_dataset = NewsGroupsDataset(train_encodings, train_labels)
valid_dataset = NewsGroupsDataset(valid_encodings, valid_labels)
# load the model and pass to CUDA
model = BertForSequenceClassification.from_pretrained(model_name, num_labels=len(target_names)).to("cuda")

def compute_metrics(pred):
    labels = pred.label_ids
    preds = pred.predictions.argmax(-1)
    # calculate accuracy using sklearn's function
    acc = accuracy_score(labels, preds)
    return {
      'accuracy': acc,
    }

training_args = TrainingArguments(
    output_dir='./results',          # output directory
    num_train_epochs=3,              # total number of training epochs
    per_device_train_batch_size=16,  # batch size per device during training
    per_device_eval_batch_size=20,   # batch size for evaluation
    warmup_steps=500,                # number of warmup steps for learning rate scheduler
    weight_decay=0.01,               # strength of weight decay
    logging_dir='./logs',            # directory for storing logs
    load_best_model_at_end=True,     # load the best model when finished training (default metric is loss)
    # but you can specify `metric_for_best_model` argument to change to accuracy or other metric
    logging_steps=200,               # log & save weights each logging_steps
    evaluation_strategy="steps",     # evaluate each `logging_steps`
)

trainer = Trainer(
    model=model,                         # the instantiated Transformers model to be trained
    args=training_args,                  # training arguments, defined above
    train_dataset=train_dataset,         # training dataset
    eval_dataset=valid_dataset,          # evaluation dataset
    compute_metrics=compute_metrics,     # the callback that computes metrics of interest
)
# train the model
trainer.train()
# evaluate the current model after training
trainer.evaluate()
# saving the fine tuned model & tokenizer
model_path = "20newsgroups-bert-base-uncased"
model.save_pretrained(model_path)
tokenizer.save_pretrained(model_path)

inference.py

from transformers import BertForSequenceClassification, BertTokenizerFast
from sklearn.model_selection import train_test_split
from sklearn.datasets import fetch_20newsgroups

model_path = "20newsgroups-bert-base-uncased"
max_length = 512

def read_20newsgroups(test_size=0.2):
  dataset = fetch_20newsgroups(subset="all", shuffle=True, remove=("headers", "footers", "quotes"))
  documents = dataset.data
  labels = dataset.target
  return train_test_split(documents, labels, test_size=test_size), dataset.target_names


(train_texts, valid_texts, train_labels, valid_labels), target_names = read_20newsgroups()

model = BertForSequenceClassification.from_pretrained(model_path, num_labels=len(target_names)).to("cuda")
tokenizer = BertTokenizerFast.from_pretrained(model_path)

def get_prediction(text):
    # prepare our text into tokenized sequence
    inputs = tokenizer(text, padding=True, truncation=True, max_length=max_length, return_tensors="pt").to("cuda")
    # perform inference to our model
    outputs = model(**inputs)
    # get output probabilities by doing softmax
    probs = outputs[0].softmax(1)
    # executing argmax function to get the candidate label
    return target_names[probs.argmax()]

# Example #1
text = """With the pace of smartphone evolution moving so fast, there's always something waiting in the wings. 
No sooner have you spied the latest handset, that there's anticipation for the next big thing. 
Here we look at those phones that haven't yet launched, the upcoming phones for 2021. 
We'll be updating this list on a regular basis, with those device rumours we think are credible and exciting."""
print(get_prediction(text))
# Example #2
text = """
A black hole is a place in space where gravity pulls so much that even light can not get out. 
The gravity is so strong because matter has been squeezed into a tiny space. This can happen when a star is dying.
Because no light can get out, people can't see black holes. 
They are invisible. Space telescopes with special tools can help find black holes. 
The special tools can see how stars that are very close to black holes act differently than other stars.
"""
print(get_prediction(text))