---
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
datasets:
- few-nerd
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: few-nerd
      type: few-nerd
      config: supervised
      split: validation
      args: supervised
    metrics:
    - name: Precision
      type: precision
      value: 0.7833402370948971
    - name: Recall
      type: recall
      value: 0.8147760612215589
    - name: F1
      type: f1
      value: 0.798748969206943
    - name: Accuracy
      type: accuracy
      value: 0.9425415670481714
---

<!-- 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-finetuned-ner

This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co./FacebookAI/roberta-large) on the few-nerd dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2154
- Precision: 0.7833
- Recall: 0.8148
- F1: 0.7987
- Accuracy: 0.9425

## 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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.1957        | 1.0   | 32942 | 0.1963          | 0.7533    | 0.7992 | 0.7756 | 0.9386   |
| 0.1596        | 2.0   | 65884 | 0.2025          | 0.7768    | 0.8063 | 0.7913 | 0.9416   |
| 0.1207        | 3.0   | 98826 | 0.2154          | 0.7833    | 0.8148 | 0.7987 | 0.9425   |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0