metadata
language:
- en
license: apache-2.0
library_name: transformers
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
base_model: bert-base-uncased
model-index:
- name: bert-base-uncased-en-ner
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: test
args: conll2003
metrics:
- type: precision
value: 0.9000587199060481
name: Precision
- type: recall
value: 0.909565630192262
name: Recall
- type: f1
value: 0.9047872026444719
name: F1
- type: accuracy
value: 0.977246046543747
name: Accuracy
bert-base-uncased-en-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: 0.1434
- Precision: 0.9001
- Recall: 0.9096
- F1: 0.9048
- Accuracy: 0.9772
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
The model was trained on data that follows the IOB convention. Full tagset with indices:
{'O': 0, 'B-PER': 1, 'I-PER': 2, 'B-ORG': 3, 'I-ORG': 4, 'B-LOC': 5, 'I-LOC': 6, 'B-MISC': 7, 'I-MISC': 8}
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 0
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0759 | 1.0 | 1756 | 0.1246 | 0.8878 | 0.8973 | 0.8925 | 0.9744 |
| 0.0299 | 2.0 | 3512 | 0.1427 | 0.8911 | 0.9040 | 0.8975 | 0.9749 |
| 0.0152 | 3.0 | 5268 | 0.1434 | 0.9001 | 0.9096 | 0.9048 | 0.9772 |
Framework versions
- Transformers 4.27.2
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2