philipp-zettl/t5-small-tydiqa-en

Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: philipp-zettl
• Model type: Seq2Seq
• Language(s) (NLP):
• License: Apache 2.0
• Finetuned from model: google/flan-t5-small

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("philipp-zettl/t5-small-tydiqa-en")
model = AutoModelForSeq2SeqLM.from_pretrained("philipp-zettl/t5-small-tydiqa-en")

question = "Some question?"
# For instance retrieved using similarity search
context = "A long context ..."

inputs = [f"question: {q} context: {c}" for q, c in [[question, context]]]
model_inputs = tokenizer(inputs, 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=100)
  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", input_text)
print(f"Sample Output", sample_output_text)

Training Details

Training Data

Trained on the english samples of google-research-datasets/tydiqa using following code

from datasets import load_dataset

# Load SQuAD dataset
squad_dataset = load_dataset('google-research-datasets/tydiqa', 'secondary_task')

# Split the dataset into training and validation
train_dataset = squad_dataset['train'].filter(lambda e: any([e['id'].startswith(lang) for lang in ['english']]))
validation_dataset = squad_dataset['validation'].filter(lambda e: any([e['id'].startswith(lang) for lang in ['english']]))

Training Procedure

Preprocessing

Code for preprocessing

def preprocess_batch(batch, tokenizer, max_input_length=512, max_output_length=128):
    questions = batch['question']
    contexts = batch['context']
    answers = [answer['text'][0] for answer in batch['answers']]

    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, teacher_tokenizer), batched=True)
validation_dataset = validation_dataset.map(lambda batch: preprocess_batch(batch, teacher_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'])

Training Hyperparameters

Code of training loop:

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()

teacher_model.to(device)

# Training parameters
epochs = 3
learning_rate = 5e-5
temperature = 2.0
batch_size = 2
optimizer = torch.optim.AdamW(teacher_model.parameters(), lr=learning_rate)

# Create a data collator for padding and batching
data_collator = DataCollatorForSeq2Seq(tokenizer=teacher_tokenizer, model=teacher_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('./logs', comment='t5-base')

print("Starting training...")

# Training loop
for epoch in range(epochs):
    teacher_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
        teacher_outputs = teacher_model(input_ids=input_ids, attention_mask=attention_mask, labels=labels)
        teacher_logits = teacher_outputs.logits

        # Calculate losses
        loss = teacher_outputs.loss  # Cross-entropy loss
        writer.add_scalar("Loss/train", loss, step)

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

        total_loss += loss.item()

        # Verbose logging
        if step % 1 == 0 or step == len(train_dataloader) - 1:
            progress_bar.set_postfix({
                'step': step,
                'loss': loss.item(),
            })

            # Generate a sample output from the student model
            teacher_model.eval()
            with torch.no_grad():
                sample_output = teacher_model.generate(input_ids[:1], max_length=50)
                sample_output_text = teacher_tokenizer.decode(sample_output[0], skip_special_tokens=True)
                input_text = teacher_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)
            teacher_model.train()

    avg_loss = total_loss / len(train_dataloader)
    print(f"Epoch {epoch+1} completed. Average Loss: {avg_loss:.4f}")
    writer.add_scalar("AVG Loss/train", avg_loss, epoch)

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

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]