|
---
|
|
language: en
|
|
tags: Text Classification
|
|
license: apache-2.0
|
|
datasets:
|
|
- batterydata/paper-abstracts
|
|
metrics: glue
|
|
---
|
|
|
|
# BERT-base-cased for Battery Abstract Classification
|
|
**Language model:** bert-base-cased
|
|
**Language:** English
|
|
**Downstream-task:** Text Classification
|
|
**Training data:** training\_data.csv
|
|
**Eval data:** val\_data.csv
|
|
**Code:** See [example](https://github.com/ShuHuang/batterybert)
|
|
**Infrastructure**: 8x DGX A100
|
|
## Hyperparameters
|
|
```
|
|
batch_size = 32
|
|
n_epochs = 15
|
|
base_LM_model = "bert-base-cased"
|
|
learning_rate = 2e-5
|
|
```
|
|
## Performance
|
|
```
|
|
"Validation accuracy": 96.84,
|
|
"Test accuracy": 96.83,
|
|
```
|
|
|
|
## Usage
|
|
### In Transformers
|
|
```python
|
|
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
|
|
model_name = "batterydata/bert-base-cased-abstract"
|
|
|
|
# a) Get predictions
|
|
nlp = pipeline('text-classification', model=model_name, tokenizer=model_name)
|
|
input = {'The typical non-aqueous electrolyte for commercial Li-ion cells is a solution of LiPF6 in linear and cyclic carbonates.'}
|
|
res = nlp(input)
|
|
|
|
# b) Load model & tokenizer
|
|
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
```
|
|
## Authors
|
|
Shu Huang: `sh2009 [at] cam.ac.uk`
|
|
|
|
Jacqueline Cole: `jmc61 [at] cam.ac.uk`
|
|
|
|
## Citation
|
|
BatteryBERT: A Pre-trained Language Model for Battery Database Enhancement |
