# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("the-bee/bert-finetuned-ner")
model = AutoModelForTokenClassification.from_pretrained("the-bee/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: 0.0594
- Precision: 0.9331
- Recall: 0.9529
- F1: 0.9429
- 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: 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 |
|---|---|---|---|---|---|---|---|
| 0.0872 | 1.0 | 1756 | 0.0631 | 0.9128 | 0.9359 | 0.9242 | 0.9827 |
| 0.0338 | 2.0 | 3512 | 0.0578 | 0.9322 | 0.9510 | 0.9415 | 0.9867 |
| 0.0174 | 3.0 | 5268 | 0.0594 | 0.9331 | 0.9529 | 0.9429 | 0.9872 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1
- Downloads last month
- 3
Dataset used to train the-bee/bert-finetuned-ner
Evaluation results
- Precision on conll2003self-reported0.933
- Recall on conll2003self-reported0.953
- F1 on conll2003self-reported0.943
- Accuracy on conll2003self-reported0.987
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="the-bee/bert-finetuned-ner")