Token Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("jperezv/bert-finetuned-ner")
model = AutoModelForTokenClassification.from_pretrained("jperezv/bert-finetuned-ner")Quick Links
bert-finetuned-ner
This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0627
- Precision: 0.9389
- Recall: 0.9524
- F1: 0.9456
- Accuracy: 0.9866
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 |
|---|---|---|---|---|---|---|---|
| 0.0835 | 1.0 | 1756 | 0.0711 | 0.9200 | 0.9334 | 0.9266 | 0.9825 |
| 0.0329 | 2.0 | 3512 | 0.0648 | 0.9308 | 0.9485 | 0.9396 | 0.9858 |
| 0.0179 | 3.0 | 5268 | 0.0627 | 0.9389 | 0.9524 | 0.9456 | 0.9866 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 7
Dataset used to train jperezv/bert-finetuned-ner
Evaluation results
- Precision on conll2003self-reported0.939
- Recall on conll2003self-reported0.952
- F1 on conll2003self-reported0.946
- Accuracy on conll2003self-reported0.987
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="jperezv/bert-finetuned-ner")