---
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-uncased-finetuned-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: 0.9398762157382847
    - name: Recall
      type: recall
      value: 0.9513368385725472
    - name: F1
      type: f1
      value: 0.9455718018568967
    - name: Accuracy
      type: accuracy
      value: 0.9865442356267972
---

<!-- 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-uncased-finetuned-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: 0.0727
- Precision: 0.9399
- Recall: 0.9513
- F1: 0.9456
- Accuracy: 0.9865

## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.0   | 439  | 0.0697          | 0.8960    | 0.9187 | 0.9072 | 0.9799   |
| 0.185         | 2.0   | 878  | 0.0607          | 0.9227    | 0.9384 | 0.9304 | 0.9837   |
| 0.0471        | 3.0   | 1317 | 0.0560          | 0.9341    | 0.9433 | 0.9387 | 0.9858   |
| 0.0263        | 4.0   | 1756 | 0.0610          | 0.9300    | 0.9447 | 0.9373 | 0.9853   |
| 0.0161        | 5.0   | 2195 | 0.0629          | 0.9361    | 0.9516 | 0.9437 | 0.9859   |
| 0.0112        | 6.0   | 2634 | 0.0676          | 0.9372    | 0.9490 | 0.9431 | 0.9860   |
| 0.0076        | 7.0   | 3073 | 0.0697          | 0.9348    | 0.9487 | 0.9417 | 0.9859   |
| 0.0056        | 8.0   | 3512 | 0.0706          | 0.9364    | 0.9497 | 0.9430 | 0.9862   |
| 0.0056        | 9.0   | 3951 | 0.0719          | 0.9381    | 0.9497 | 0.9439 | 0.9864   |
| 0.0038        | 10.0  | 4390 | 0.0727          | 0.9399    | 0.9513 | 0.9456 | 0.9865   |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1