|
--- |
|
license: apache-2.0 |
|
base_model: albert-base-v2 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- squad_v2 |
|
model-index: |
|
- name: albert-base-v2-finetuned-squad2 |
|
results: [] |
|
language: |
|
- en |
|
metrics: |
|
- exact_match |
|
- f1 |
|
pipeline_tag: zero-shot-classification |
|
--- |
|
|
|
<!-- 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 |
|
|
|
ALBERTbase fine-tuned on SQuAD 2.0 : Encoder-based Transformer Language model, pretrained with Parameter Reduction techniques and Sentence Order Prediction<br> |
|
Suitable for Question-Answering tasks, predicts answer spans within the context provided.<br> |
|
|
|
**Language model:** albert-base-v2 |
|
**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/bert-base-uncased-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: 78.12684241556472, |
|
f1: 81.54753481344116, |
|
total: 11873, |
|
HasAns_exact: 73.80229419703105, |
|
HasAns_f1: 80.65348867071317, |
|
HasAns_total: 5928, |
|
NoAns_exact: 82.4390243902439, |
|
NoAns_f1: 82.4390243902439, |
|
NoAns_total: 5945, |
|
best_exact: 78.12684241556472, |
|
best_exact_thresh: 0.9990358352661133, |
|
best_f1: 81.54753481344157, |
|
best_f1_thresh: 0.9990358352661133, |
|
total_time_in_seconds: 248.44505145400035, |
|
samples_per_second: 47.78923923223437, |
|
latency_in_seconds: 0.020925212789859374 |
|
``` |
|
### 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.92 | 1.0 | 8248 | 0.8960 | |
|
| 0.6593 | 2.0 | 16496 | 0.8548 | |
|
| 0.4314 | 3.0 | 24744 | 0.9900 | |
|
|
|
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad_v2 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9900 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.3 |
|
- Tokenizers 0.13.3 |
