---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-uncased-finetuned-ner
  results: []
---

<!-- 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: 0.0616
- Precision: 0.9217
- Recall: 0.9375
- F1: 0.9295
- Accuracy: 0.9837

## 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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: IPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- total_eval_batch_size: 5
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- training precision: Mixed Precision

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0813        | 1.0   | 877  | 0.0659          | 0.9113    | 0.9206 | 0.9159 | 0.9812   |
| 0.0567        | 2.0   | 1754 | 0.0635          | 0.9194    | 0.9351 | 0.9272 | 0.9828   |
| 0.0151        | 3.0   | 2631 | 0.0616          | 0.9217    | 0.9375 | 0.9295 | 0.9837   |


### Framework versions

- Transformers 4.20.1
- Pytorch 1.10.0+cpu
- Datasets 2.7.1
- Tokenizers 0.12.1