---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-distilled-squad
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# distilbert-base-uncased-distilled-squad

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1892

## Model description

The DistilBERT model was proposed in the blog post Smaller, faster, cheaper, lighter: Introducing DistilBERT, adistilled version of BERT, and the paper DistilBERT, adistilled version of BERT: smaller, faster, cheaper and lighter. DistilBERT is a small, fast, cheap and light Transformer model trained by distilling BERT base. It has 40% less parameters than bert-base-uncased, runs 60% faster while preserving over 95% of BERT's performances as measured on the GLUE language understanding benchmark.

This model is a fine-tune checkpoint of DistilBERT-base-uncased, fine-tuned using (a second step of) knowledge distillation on SQuAD v1.1.
## Results are my own reproduction of the development by Hugging Face.

## How to Get Started with the Model
Use the code below:

from transformers import pipeline
question_answerer = pipeline("question-answering", model='distilbert-base-uncased-distilled-squad')

context = r"""
Extractive Question Answering is the task of extracting an answer from a text given a question. An example     of a
question answering dataset is the SQuAD dataset, which is entirely based on that task. If you would like to fine-tune
a model on a SQuAD task, you may leverage the examples/pytorch/question-answering/run_squad.py script.
"""

result = question_answerer(question="What is a good example of a question answering dataset?",     context=context)
print(
f"Answer: '{result['answer']}', score: {round(result['score'], 4)}, start: {result['start']}, end: {result['end']}"

# Here is how to use this model in PyTorch:

from transformers import DistilBertTokenizer, DistilBertForQuestionAnswering
import torch
tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased-distilled-squad')
model = DistilBertForQuestionAnswering.from_pretrained('distilbert-base-uncased-distilled-squad')

question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"

inputs = tokenizer(question, text, return_tensors="pt")
with torch.no_grad():
    outputs = model(**inputs)

answer_start_index = torch.argmax(outputs.start_logits)
answer_end_index = torch.argmax(outputs.end_logits)

predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
tokenizer.decode(predict_answer_tokens)

# And in TensorFlow:

from transformers import DistilBertTokenizer, TFDistilBertForQuestionAnswering
import tensorflow as tf

tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased-distilled-squad")
model = TFDistilBertForQuestionAnswering.from_pretrained("distilbert-base-uncased-distilled-squad")

question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"

inputs = tokenizer(question, text, return_tensors="tf")
outputs = model(**inputs)

answer_start_index = int(tf.math.argmax(outputs.start_logits, axis=-1)[0])
answer_end_index = int(tf.math.argmax(outputs.end_logits, axis=-1)[0])

predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
tokenizer.decode(predict_answer_tokens)

## Uses:
This model can be used for question answering.

## Intended uses & limitations

CONTENT WARNING: Readers should be aware that language generated by this model can be disturbing or offensive to some and can propagate historical and current stereotypes.

## Training and evaluation data

This model reaches a F1 score of 82.75539002485876 and 'exact_match': 73.66130558183538 on the [SQuAD v1.1] dev set (for comparison, Bert bert-base-uncased version reaches a F1 score of 88.5).d

## Training procedure

Preprocessing
See the distilbert-base-uncased model card for further details.

Pretraining
See the distilbert-base-uncased model card for further details.

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.2559        | 1.0   | 5533 | 1.1892          |


### Framework versions

- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1