# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("linearch/bert-finetuned-ner")
model = AutoModelForTokenClassification.from_pretrained("linearch/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: nan
- Precision: 0.9299
- Recall: 0.9493
- F1: 0.9395
- Accuracy: 0.9863
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 |
|---|---|---|---|---|---|---|---|
| 0.2268 | 1.0 | 878 | nan | 0.9016 | 0.9362 | 0.9186 | 0.9820 |
| 0.0462 | 2.0 | 1756 | nan | 0.9283 | 0.9482 | 0.9381 | 0.9860 |
| 0.0248 | 3.0 | 2634 | nan | 0.9299 | 0.9493 | 0.9395 | 0.9863 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 4
Model tree for linearch/bert-finetuned-ner
Base model
google-bert/bert-base-casedDataset used to train linearch/bert-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.930
- Recall on conll2003validation set self-reported0.949
- F1 on conll2003validation set self-reported0.940
- Accuracy on conll2003validation set self-reported0.986
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="linearch/bert-finetuned-ner")