summarize_train.py

import transformers
from datasets import load_dataset, load_metric
import datasets
import random
import pandas as pd
from IPython.display import display, HTML
from transformers import AutoTokenizer
from transformers import AutoModelForSeq2SeqLM, DataCollatorForSeq2Seq, Seq2SeqTrainingArguments, Seq2SeqTrainer


model_checkpoint = "t5-small"

raw_datasets = load_dataset("xsum")
metric = load_metric("rouge")



def show_random_elements(dataset, num_examples=5):
    assert num_examples <= len(dataset), "Can't pick more elements than there are in the dataset."
    picks = []
    for _ in range(num_examples):
        pick = random.randint(0, len(dataset) - 1)
        while pick in picks:
            pick = random.randint(0, len(dataset) - 1)
        picks.append(pick)

    df = pd.DataFrame(dataset[picks])
    for column, typ in dataset.features.items():
        if isinstance(typ, datasets.ClassLabel):
            df[column] = df[column].transform(lambda i: typ.names[i])
    display(HTML(df.to_html()))

tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
print(transformers.__version__)

if model_checkpoint in ["t5-small", "t5-base", "t5-larg", "t5-3b", "t5-11b"]:
    prefix = "summarize: "
else:
    prefix = ""

max_input_length = 1024
max_target_length = 128

def preprocess_function(examples):
    inputs = [prefix + doc for doc in examples["document"]]
    model_inputs = tokenizer(inputs, max_length=max_input_length, truncation=True)

    # Setup the tokenizer for targets
    with tokenizer.as_target_tokenizer():
        labels = tokenizer(examples["summary"], max_length=max_target_length, truncation=True)

    model_inputs["labels"] = labels["input_ids"]
    return model_inputs


model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)

batch_size = 16
model_name = model_checkpoint.split("/")[-1]
args = Seq2SeqTrainingArguments(
    f"{model_name}-finetuned-xsum",
    evaluation_strategy = "epoch",
    learning_rate=2e-5,
    per_device_train_batch_size=batch_size,
    per_device_eval_batch_size=batch_size,
    weight_decay=0.01,
    save_total_limit=3,
    num_train_epochs=1,
    predict_with_generate=True,
    fp16=True,
    push_to_hub=True,
)

import nltk
import numpy as np


def compute_metrics(eval_pred):
    predictions, labels = eval_pred
    decoded_preds = tokenizer.batch_decode(predictions, skip_special_tokens=True)
    # Replace -100 in the labels as we can't decode them.
    labels = np.where(labels != -100, labels, tokenizer.pad_token_id)
    decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)

    # Rouge expects a newline after each sentence
    decoded_preds = ["\n".join(nltk.sent_tokenize(pred.strip())) for pred in decoded_preds]
    decoded_labels = ["\n".join(nltk.sent_tokenize(label.strip())) for label in decoded_labels]

    result = metric.compute(predictions=decoded_preds, references=decoded_labels, use_stemmer=True)
    # Extract a few results
    result = {key: value.mid.fmeasure * 100 for key, value in result.items()}

    # Add mean generated length
    prediction_lens = [np.count_nonzero(pred != tokenizer.pad_token_id) for pred in predictions]
    result["gen_len"] = np.mean(prediction_lens)

    return {k: round(v, 4) for k, v in result.items()}

trainer = Seq2SeqTrainer(
    model,
    args,
    train_dataset=tokenized_datasets["train"],
    eval_dataset=tokenized_datasets["validation"],
    data_collator=data_collator,
    tokenizer=tokenizer,
    compute_metrics=compute_metrics
)