---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-cased-finetuned-conll2003
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: conll2003
      type: conll2003
      args: conll2003
    metrics:
    - name: Precision
      type: precision
      value: 0.9409771754636234
    - name: Recall
      type: recall
      value: 0.946886775524852
    - name: F1
      type: f1
      value: 0.9439227260531259
    - name: Accuracy
      type: accuracy
      value: 0.9859745687878966
---

<!-- 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. -->

# bert-base-cased-finetuned-conll2003

This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0643
- Precision: 0.9410
- Recall: 0.9469
- F1: 0.9439
- Accuracy: 0.9860

## 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: 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: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2349        | 0.57  | 500  | 0.0885          | 0.8957    | 0.8980 | 0.8968 | 0.9747   |
| 0.0822        | 1.14  | 1000 | 0.0774          | 0.9184    | 0.9219 | 0.9202 | 0.9802   |
| 0.0476        | 1.71  | 1500 | 0.0683          | 0.9345    | 0.9325 | 0.9335 | 0.9833   |
| 0.0368        | 2.28  | 2000 | 0.0653          | 0.9333    | 0.9430 | 0.9381 | 0.9847   |
| 0.028         | 2.85  | 2500 | 0.0670          | 0.9279    | 0.9342 | 0.9311 | 0.9835   |
| 0.0171        | 3.42  | 3000 | 0.0643          | 0.9410    | 0.9469 | 0.9439 | 0.9860   |
| 0.0149        | 3.99  | 3500 | 0.0667          | 0.9369    | 0.9477 | 0.9422 | 0.9856   |
| 0.0088        | 4.56  | 4000 | 0.0698          | 0.9360    | 0.9473 | 0.9416 | 0.9855   |


### Framework versions

- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1