README.md

---
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
datasets:
- squad_v2
model-index:
- name: deberta-v3-base-finetuned-squad2
  results:
  - task:
      name: Question Answering
      type: question-answering
    dataset:
      type: squad_v2
      name: SQuAD 2
      config: squad_v2
      split: validation
      args: en
    metrics:
    - type: exact_match
      value: 84.56161037648447
      name: Exact-Match
      verified: true
    - type: f1
      value: 87.81110592215731
      name: F1-score
      verified: true
language:
- en
pipeline_tag: question-answering
metrics:
- exact_match
- f1
---

<!-- 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. -->

## Model description

DeBERTa-v3-base fine-tuned on SQuAD 2.0 : Encoder-based Transformer Language model.
The DeBERTa V3 base model comes with 12 layers and a hidden size of 768. 
It has only 86M backbone parameters with a vocabulary containing 128K tokens which introduces 98M parameters in the Embedding layer. 
This model was trained using the 160GB data as DeBERTa V2.
Suitable for Question-Answering tasks, predicts answer spans within the context provided.<br>

**Language model:** microsoft/deberta-v3-base  
**Language:** English  
**Downstream-task:** Question-Answering  
**Training data:** Train-set SQuAD 2.0  
**Evaluation data:** Evaluation-set SQuAD 2.0   
**Hardware Accelerator used**: GPU Tesla T4

## Intended uses & limitations

For Question-Answering - 

```python
!pip install transformers
from transformers import pipeline
model_checkpoint = "IProject-10/deberta-v3-base-finetuned-squad2"
question_answerer = pipeline("question-answering", model=model_checkpoint)

context = """
🤗 Transformers is backed by the three most popular deep learning libraries — Jax, PyTorch and TensorFlow — with a seamless integration
between them. It's straightforward to train your models with one before loading them for inference with the other.
"""

question = "Which deep learning libraries back 🤗 Transformers?"
question_answerer(question=question, context=context)
```

## Results

Evaluation on SQuAD 2.0 validation dataset:

```
 exact: 84.56161037648447,
 f1: 87.81110592215731,
 total: 11873,
 HasAns_exact: 81.62955465587045,
 HasAns_f1: 88.13786447600818,
 HasAns_total: 5928,
 NoAns_exact: 87.48528174936922,
 NoAns_f1: 87.48528174936922,
 NoAns_total: 5945,
 best_exact: 84.56161037648447,
 best_exact_thresh: 0.9994288682937622,
 best_f1: 87.81110592215778,
 best_f1_thresh: 0.9994288682937622,
 total_time_in_seconds: 336.43560706100106,
 samples_per_second: 35.29055709566211,
 latency_in_seconds: 0.028336191953255374
```

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 3e-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: 3

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.7299        | 1.0   | 8217  | 0.7246          |
| 0.5104        | 2.0   | 16434 | 0.7321          |
| 0.3547        | 3.0   | 24651 | 0.8493          |

This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the squad_v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8493
  
### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3