metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-conll-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: 0.9371267418712674
- name: Recall
type: recall
value: 0.9506900033658701
- name: F1
type: f1
value: 0.9438596491228071
- name: Accuracy
type: accuracy
value: 0.986504385706717
bert-finetuned-conll-ner
This model is a fine-tuned version of bert-base-cased on the conll2003 dataset.
This uses the Cased version of Bert, so keep the casing unchanged before using this model
It achieves the following results on the evaluation set:
- Loss: 0.0615
- Precision: 0.9371
- Recall: 0.9507
- F1: 0.9439
- 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: 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 |
---|---|---|---|---|---|---|---|
0.0766 | 1.0 | 1756 | 0.0793 | 0.9100 | 0.9360 | 0.9228 | 0.9795 |
0.0416 | 2.0 | 3512 | 0.0602 | 0.9283 | 0.9473 | 0.9377 | 0.9857 |
0.0253 | 3.0 | 5268 | 0.0615 | 0.9371 | 0.9507 | 0.9439 | 0.9865 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1