metadata
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: 0.9449011330815374
- name: Recall
type: recall
value: 0.9515605772457769
- name: F1
type: f1
value: 0.9482191628114375
- name: Accuracy
type: accuracy
value: 0.987243236373457
BERT-ner
This model is a fine-tuned version of bert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0664
- Precision: 0.9449
- Recall: 0.9516
- F1: 0.9482
- Accuracy: 0.9872
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0252 | 1.0 | 878 | 0.0652 | 0.9414 | 0.9419 | 0.9417 | 0.9854 |
| 0.0121 | 2.0 | 1756 | 0.0615 | 0.9407 | 0.9498 | 0.9452 | 0.9867 |
| 0.0079 | 3.0 | 2634 | 0.0664 | 0.9449 | 0.9516 | 0.9482 | 0.9872 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3