---
library_name: transformers
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- ncbi_disease
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: ncbi_disease
      type: ncbi_disease
      config: ncbi_disease
      split: validation
      args: ncbi_disease
    metrics:
    - name: Precision
      type: precision
      value: 0.7806004618937644
    - name: Recall
      type: recall
      value: 0.8589580686149937
    - name: F1
      type: f1
      value: 0.8179068360556564
    - name: Accuracy
      type: accuracy
      value: 0.9826963774430474
---

<!-- 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 [bert-base-cased](https://huggingface.co/bert-base-cased) on the ncbi_disease dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0745
- Precision: 0.7806
- Recall: 0.8590
- F1: 0.8179
- Accuracy: 0.9827

## 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: 8
- eval_batch_size: 8
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.1184        | 1.0   | 680  | 0.0607          | 0.7512    | 0.8285 | 0.7879 | 0.9823   |
| 0.044         | 2.0   | 1360 | 0.0616          | 0.7635    | 0.8450 | 0.8022 | 0.9832   |
| 0.0159        | 3.0   | 2040 | 0.0745          | 0.7806    | 0.8590 | 0.8179 | 0.9827   |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1