---
license: mit
datasets:
- philipp-zettl/long-qa
language:
- en
library_name: transformers
pipeline_tag: text2text-generation
widget:
  - text: "question: How many models are in the hub? context: The Hugging Face Hub is a
      platform with over 350k models, 75k datasets, and 150k demo apps (Spaces),
      all open source and publicly available, in an online platform where people
      can easily collaborate and build ML together. The Hub works as a central
      place where anyone can explore, experiment, collaborate, and build
      technology with Machine Learning. Are you ready to join the path towards
      open source Machine Learning? 🤗"
    example_title: 🤗 Hub
  - text: "question: What type of data is available? context:
      🤗 Datasets is a library for easily accessing and sharing datasets for Audio,
      Computer Vision, and Natural Language Processing (NLP) tasks. Load a dataset
      in a single line of code, and use our powerful data processing methods to 
      quickly get your dataset ready for training in a deep learning model. Backed
      by the Apache Arrow format, process large datasets with zero-copy reads without
      any memory constraints for optimal speed and efficiency. We also feature a
      deep integration with the Hugging Face Hub, allowing you to easily load
      and share a dataset with the wider machine learning community. Find your
      dataset today on the Hugging Face Hub, and take an in-depth look inside of
      it with the live viewer."
    example_title: 🤗 datasets
---

# Model Card for t5-small-long-qa

<!-- Provide a quick summary of what the model is/does. -->

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->
This model was trained to generate answers for questions out of a given context.


- **Developed by:** [philipp-zettl](https://huggingface.co/philipp-zettl)
- **Model type:** Transformer (T5)
- **Language(s) (NLP):** English
- **License:** M.I.T
- **Finetuned from model [optional]:** [google/flan-t5-small](https://huggingface.co/google/flan-t5-small)

### Model Sources [optional]

<!-- Provide the basic links for the model. -->
Fine-tune of the amazing [google/flan-t5-small](https://huggingface.co/google/flan-t5-small)

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
It's intended to use the model to answers for questions from given context.
The context should not exceed the model's _context_ length.

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

No bias evaluation was performed on this model.

## How to Get Started with the Model

Use the code below to get started with the model.

```python
context = "This is a long text based of multiple concatenated paragraphs."
question = "My question about something mentioned inside the context."

model_inputs = tokenizer([f"question: {question} context: {context}"], max_length=512, padding=True, truncation=True)
input_ids = torch.tensor(model_inputs['input_ids']).to(device)
attention_mask = torch.tensor(model_inputs['attention_mask']).to(device)
with torch.no_grad():
    sample_output = model.generate(input_ids[:1], max_length=85)
    sample_output_text = tokenizer.decode(sample_output[0], skip_special_tokens=True)
    input_text = tokenizer.decode(input_ids[0], skip_special_tokens=True)
    print(f"Sample Input:\n \"{input_text}\"\n\n")
    print(f"Model Output: \"{sample_output_text}\"")
```

## Training Details

### Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

This model was trained on [philipp-zettl/long-qa](https://huggingface.co/datasets/philipp-zettl/long-qa).

A synthetic data set created from [philipp-zettl/qg-tidyqa_squad2](https://huggingface.co/datasets/philipp-zettl/qg-tydiqa_squad2) using [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct).

The data set was created by prompting Phi-3 using the prompt template
```python
msg = f"""
Answer the following question using the content provided in the context.
Do not answer questions where the answer isn't inside the context.


Question: {sample['question']}
Context: {sample['context']}
"""
```

After generating synthetic answers, the data set was manually corrected and validated to ensure high quality as well as consistent longer answers than the original data sets.

### Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
Below you can find the full training pipeline used to achieve this fine-tune.

```python
import torch
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

# Base model (e.g., T5-large)
# https://huggingface.co/collections/google/flan-t5-release-65005c39e3201fff885e22fb
model_name = 'google/flan-t5-small'
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Move only the student model to GPU if available
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = model.to(device)
```

Load dataset
```python
from datasets import load_dataset

# Load dataset
ds = load_dataset('philipp-zettl/long-qa')

# Split the dataset into training and validation
train_dataset = ds['train']
validation_dataset = ds['test']
```

Preprocessing: tokenize inputs and labels for faster training cycles, i.e. no need for tokenization during training anymore
```python
def preprocess_batch(batch, tokenizer, max_input_length=512, max_output_length=128):
    questions = batch['question']
    contexts = batch['context']
    answers = batch['answer']

    inputs = [f"question: {q} context: {c}" for q, c in zip(questions, contexts)]
    model_inputs = tokenizer(inputs, max_length=max_input_length, padding=True, truncation=True)

    labels = tokenizer(answers, max_length=max_output_length, padding=True, truncation=True)
    model_inputs['labels'] = labels['input_ids']

    return model_inputs

# Tokenize the dataset
train_dataset = train_dataset.map(lambda batch: preprocess_batch(batch, tokenizer), batched=True)
validation_dataset = validation_dataset.map(lambda batch: preprocess_batch(batch, tokenizer), batched=True)

# Set format for PyTorch
train_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'labels'])
validation_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'labels'])
```

The train loop
```python
from tqdm import tqdm
from transformers import AdamW, DataCollatorForSeq2Seq
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

torch.cuda.empty_cache()

model_name = 'google/flan-t5-small'
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Move only the student model to GPU if available
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = model.to(device)

# Training parameters
epochs = 50
learning_rate = 3e-5
temperature = 2.0
batch_size = 8
optimizer = torch.optim.AdamW(model.parameters(), lr=learning_rate)

# Create a data collator for padding and batching
data_collator = DataCollatorForSeq2Seq(tokenizer=tokenizer, model=model)

# Create DataLoaders with the data collator
train_dataloader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, collate_fn=data_collator)
validation_dataloader = DataLoader(validation_dataset, batch_size=batch_size, collate_fn=data_collator)

writer = SummaryWriter(comment='t5-small-long-qa')

# Store losses and learning rates
train_losses = []
val_losses = []
learning_rates = []

print("Starting training...")

# Training loop
for epoch in range(epochs):
    model.train()
    total_loss = 0
    print(f"Epoch {epoch+1}/{epochs}")

    progress_bar = tqdm(train_dataloader, desc="Training", leave=False)

    for step, batch in enumerate(progress_bar):
        # Move student inputs to GPU
        input_ids = batch['input_ids'].to(device)
        attention_mask = batch['attention_mask'].to(device)
        labels = batch['labels'].to(device)

        # Teacher forward pass on CPU
        outputs = model(input_ids=input_ids, attention_mask=attention_mask, labels=labels)
        logits = outputs.logits

        # Calculate losses
        loss = outputs.loss  # Cross-entropy loss
        writer.add_scalar("Loss/train", loss, epoch * len(train_dataloader) + step)

        # Backpropagation
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_loss += loss.item()

        # Verbose logging
        if step % len(train_dataloader)//10 == 1 or step == len(train_dataloader) - 1:
            progress_bar.set_postfix({
                'step': step,
                'loss': loss.item(),
            })

            # Generate a sample output from the student model
            model.eval()
            with torch.no_grad():
                sample_output = model.generate(input_ids[:1], max_length=50)
                sample_output_text = tokenizer.decode(sample_output[0], skip_special_tokens=True)
                input_text = tokenizer.decode(input_ids[0], skip_special_tokens=True)
                writer.add_text(f"Sample Input", input_text, step)
                writer.add_text(f"Sample Output", sample_output_text, step)
            model.train()

    
    avg_train_loss = total_loss / len(train_dataloader)
    train_losses.append(avg_train_loss)
    learning_rates.append(optimizer.param_groups[0]['lr'])

    # Validation step
    model.eval()
    total_val_loss = 0
    with torch.no_grad():
        for batch in validation_dataloader:
            input_ids = batch['input_ids'].to(device)
            attention_mask = batch['attention_mask'].to(device)
            labels = batch['labels'].to(device)

            outputs = model(input_ids=input_ids, attention_mask=attention_mask, labels=labels)
            val_loss = outputs.loss
            total_val_loss += val_loss.item()

    avg_val_loss = total_val_loss / len(validation_dataloader)
    val_losses.append(avg_val_loss)

    writer.add_scalar("AVG Loss/train", avg_train_loss, epoch)
    writer.add_scalar("AVG Loss/val", avg_val_loss, epoch)

    print(f"Epoch {epoch+1} completed. Avg Train Loss: {avg_train_loss:.4f}, Avg Val Loss: {avg_val_loss:.4f}")


print("Training complete.")
writer.close()
```