---
license: apache-2.0
language: en
tags:
- generated_from_trainer
datasets:
- squad_v2
model-index:
- name: distilroberta-base-squad_v2
  results:
  - task:
      name: Question Answering
      type: question-answering
    dataset:
      type: squad_v2  # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
      name: The Stanford Question Answering Dataset
      args: en
    metrics:
        - type: eval_exact
          value: 65.2405
        - type: eval_f1
          value: 68.6265
        - type: eval_HasAns_exact
          value: 67.5776
        - type: eval_HasAns_f1
          value: 74.3594
        - type: eval_NoAns_exact
          value: 62.91
        - type: eval_NoAns_f1
          value: 62.91
---

# distilroberta-base-squad_v2

This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the squad_v2 dataset.

## Model description

This model is fine-tuned on the extractive question answering task -- The Stanford Question Answering Dataset -- [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/).

For convenience this model is prepared to be used with the frameworks `PyTorch`, `Tensorflow` and `ONNX`.

## Intended uses & limitations

This model can handle mismatched question-context pairs. Make sure to specify `handle_impossible_answer=True` when using `QuestionAnsweringPipeline`.

__Example usage:__

```python
>>> from transformers import AutoModelForQuestionAnswering, AutoTokenizer, QuestionAnsweringPipeline
>>> model = AutoModelForQuestionAnswering.from_pretrained("squirro/distilroberta-base-squad_v2")
>>> tokenizer = AutoTokenizer.from_pretrained("squirro/distilroberta-base-squad_v2")
>>> qa_model = QuestionAnsweringPipeline(model, tokenizer)
>>> qa_model(
>>>    question="What's your name?",
>>>    context="My name is Clara and I live in Berkeley.",
>>>    handle_impossible_answer=True  # important!
>>> )
{'score': 0.9498472809791565, 'start': 11, 'end': 16, 'answer': 'Clara'}
```

## Training and evaluation data

Training and evaluation was done on [SQuAD2.0](https://huggingface.co/datasets/squad_v2).

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- distributed_type: tpu
- num_devices: 8
- total_train_batch_size: 512
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0

### Training results

| Metric                   |        Value |
|:-------------------------|-------------:|
| epoch                    |      3       |
| eval_HasAns_exact        |     67.5776  |
| eval_HasAns_f1           |     74.3594  |
| eval_HasAns_total        |   5928       |
| eval_NoAns_exact         |     62.91    |
| eval_NoAns_f1            |     62.91    |
| eval_NoAns_total         |   5945       |
| eval_best_exact          |     65.2489  |
| eval_best_exact_thresh   |      0       |
| eval_best_f1             |     68.6349  |
| eval_best_f1_thresh      |      0       |
| eval_exact               |     65.2405  |
| eval_f1                  |     68.6265  |
| eval_samples             |  12165       |
| eval_total               |  11873       |
| train_loss               |      1.40336 |
| train_runtime            |   1365.28    |
| train_samples            | 131823       |
| train_samples_per_second |    289.662   |
| train_steps_per_second   |      0.567   |

### Framework versions

- Transformers 4.17.0.dev0
- Pytorch 1.9.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.6