---
tags:
- generated_from_trainer
model-index:
- name: ibert-roberta-base-finetuned-WikiNeural
  results: []
datasets:
- Babelscape/wikineural
language:
- en
metrics:
- accuracy
- f1
- recall
- precision
- seqeval
pipeline_tag: token-classification
---

# ibert-roberta-base-finetuned-WikiNeural

This model is a fine-tuned version of [kssteven/ibert-roberta-base](https://huggingface.co/kssteven/ibert-roberta-base).

It achieves the following results on the evaluation set:
- Loss: 0.0878
- Loc
  - Precision: 0.9249338624338624
  - Recall: 0.9393786733837112
  - F1: 0.9321003082562693
  - Number: 5955
- Misc
  - Precision: 0.8304751697034656
  - Recall: 0.9185931634064414
  - F1: 0.8723144760296463
  - Number: 5061
- Org
  - Precision: 0.9283453237410072
  - Recall: 0.9353435778486517
  - F1: 0.9318313113807049
  - Number: 3449
- Per
  - Precision: 0.9698098412076064
  - Recall: 0.9495201535508637
  - F1: 0.9595577538551062
  - Number: 5210
- Overall
  - Precision: 0.9107
  - Recall: 0.9360
  - F1: 0.9232
  - Accuracy: 0.9909

## Model description

For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Token%20Classification/Monolingual/WikiNeural%20-%20Transformer%20Comparison/POS%20Project%20with%20Wikineural%20Dataset%20-%20I-BERT%20Transformer.ipynb

## Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

## Training and evaluation data

Dataset Source: https://huggingface.co/datasets/Babelscape/wikineural

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-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: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss | Loc Precision | Loc Recall | Loc F1 | Loc Number | Misc Precision | Misc Recall | Misc F1 | Misc Number | Org Precision | Org Recall | Org F1 | Org Number | Per Precision | Per Recall | Per F1 | Per Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:--------:|:---------:|:-----------------:|:--------------:|:----------:|:----------------:|:--------------:|:----------:|:----------------:|:--------------:|:----------:|:----------------:|:--------------:|:----------:|:----------------:|:--------------:|:----------:|:----------------:|
| 0.1092        | 1.0   | 5795  | 0.0987          | 0.9125 | 0.9328 | 0.9225 | 5955 | 0.8003 | 0.9091 | 0.8512 | 5061 | 0.9143 | 0.9278 | 0.9210 | 3449 | 0.9714 | 0.9395 | 0.9552 | 5210 | 0.8957 | 0.9276 | 0.9114 | 0.9890 |
| 0.0723        | 2.0   | 11590 | 0.0878          | 0.9249 | 0.9394 | 0.9321 | 5955 | 0.8305 | 0.9186 | 0.8723 | 5061 | 0.9283 | 0.9353 | 0.9318 | 3449 | 0.9698 | 0.9495 | 0.9596 | 5210 | 0.9107 | 0.9360 | 0.9232 | 0.9909 |

* All values in the above chart arerounded to nearest ten-thousandth.

### Framework versions

- Transformers 4.28.1
- Pytorch 2.0.1
- Datasets 2.13.0
- Tokenizers 0.13.3