---
license: apache-2.0
base_model: Flamenco43/MatBERT
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: MatBERT-conll2003
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: conll2003
      type: conll2003
      config: conll2003
      split: validation
      args: conll2003
    metrics:
    - name: Precision
      type: precision
      value: 0.8569527611443779
    - name: Recall
      type: recall
      value: 0.8670481319421071
    - name: F1
      type: f1
      value: 0.8619708884055547
    - name: Accuracy
      type: accuracy
      value: 0.9732876445621277
---

<!-- 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. -->

# MatBERT-conll2003

This model is a fine-tuned version of [Flamenco43/MatBERT](https://huggingface.co/Flamenco43/MatBERT) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0971
- Precision: 0.8570
- Recall: 0.8670
- F1: 0.8620
- Accuracy: 0.9733

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.1055        | 1.0   | 1756 | 0.0971          | 0.8570    | 0.8670 | 0.8620 | 0.9733   |
| 0.047         | 2.0   | 3512 | 0.0992          | 0.8910    | 0.8803 | 0.8856 | 0.9770   |
| 0.0206        | 3.0   | 5268 | 0.1094          | 0.9015    | 0.8930 | 0.8972 | 0.9787   |
| 0.0075        | 4.0   | 7024 | 0.1126          | 0.8958    | 0.9000 | 0.8979 | 0.9793   |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.2.1+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1