---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-ner
  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: 0.7724934572691995
    - name: Recall
      type: recall
      value: 0.767988516059573
    - name: F1
      type: f1
      value: 0.7702343996040851
    - name: Accuracy
      type: accuracy
      value: 0.9421763701654207
---

<!-- 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-ner

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2435
- Precision: 0.7725
- Recall: 0.7680
- F1: 0.7702
- Accuracy: 0.9422

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2289        | 1.0   | 878  | 0.2714          | 0.6750    | 0.6887 | 0.6818 | 0.9216   |
| 0.115         | 2.0   | 1756 | 0.2453          | 0.7099    | 0.7355 | 0.7225 | 0.9304   |
| 0.0931        | 3.0   | 2634 | 0.2474          | 0.7651    | 0.7382 | 0.7514 | 0.9380   |
| 0.068         | 4.0   | 3512 | 0.2456          | 0.7634    | 0.7524 | 0.7579 | 0.9397   |
| 0.0528        | 5.0   | 4390 | 0.2435          | 0.7725    | 0.7680 | 0.7702 | 0.9422   |


### Framework versions

- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3