---
license: mit
tags:
- generated_from_trainer
datasets:
- surrey-nlp/PLOD-filtered
metrics:
- precision
- recall
- f1
- accuracy
model_creators:
- Leonardo Zilio, Hadeel Saadany, Prashant Sharma, Diptesh Kanojia, Constantin Orasan
widget:
- text: Light dissolved inorganic carbon (DIC) resulting from the oxidation of hydrocarbons.
- text: RAFs are plotted for a selection of neurons in the dorsal zone (DZ) of auditory
    cortex in Figure 1.
- text: Images were acquired using a GE 3.0T MRI scanner with an upgrade for echo-planar
    imaging (EPI).
base_model: roberta-base
model-index:
- name: roberta-base-finetuned-ner
  results:
  - task:
      type: token-classification
      name: Token Classification
    dataset:
      name: surrey-nlp/PLOD-filtered
      type: token-classification
      args: PLODfiltered
    metrics:
    - type: precision
      value: 0.9644756447594547
      name: Precision
    - type: recall
      value: 0.9583209148378798
      name: Recall
    - type: f1
      value: 0.9613884293804785
      name: F1
    - type: accuracy
      value: 0.9575894768204436
      name: Accuracy
---

<!-- 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. -->

# roberta-base-finetuned-ner

This model is a fine-tuned version of [roberta-base](https://huggingface.co./roberta-base) on the [PLOD-filtered](surrey-nlp/PLOD-filtered) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1148
- Precision: 0.9645
- Recall: 0.9583
- F1: 0.9614
- Accuracy: 0.9576

## Model description

RoBERTa is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means
it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. 

More precisely, it was pretrained with the Masked language modeling (MLM) objective. Taking a sentence, the model
randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict
the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one
after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to
learn a bidirectional representation of the sentence.

This way, the model learns an inner representation of the English language that can then be used to extract features
useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
classifier using the features produced by the BERT model as inputs.

## Intended uses & limitations

More information needed

## Training and evaluation data

The model is fine-tuned using [PLOD-Filtered](https://huggingface.co./datasets/surrey-nlp/PLOD-filtered) dataset.
This dataset is used for training and evaluating the model. The PLOD Dataset is published at LREC 2022. The dataset can help build sequence labeling models for the task of Abbreviation Detection.

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.1179        | 1.99  | 7000  | 0.1130          | 0.9602    | 0.9517 | 0.9559 | 0.9522   |
| 0.0878        | 3.98  | 14000 | 0.1106          | 0.9647    | 0.9564 | 0.9606 | 0.9567   |
| 0.0724        | 5.96  | 21000 | 0.1149          | 0.9646    | 0.9582 | 0.9614 | 0.9576   |


### Framework versions

- Transformers 4.18.0
- Pytorch 1.10.1+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1