Token Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("donskerclass/bert-finetuned-ner")
model = AutoModelForTokenClassification.from_pretrained("donskerclass/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: 0.0597
- Precision: 0.9338
- Recall: 0.9497
- F1: 0.9417
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0784 | 1.0 | 1756 | 0.0742 | 0.9053 | 0.9302 | 0.9176 | 0.9793 |
| 0.0404 | 2.0 | 3512 | 0.0583 | 0.9294 | 0.9485 | 0.9389 | 0.9859 |
| 0.0255 | 3.0 | 5268 | 0.0597 | 0.9338 | 0.9497 | 0.9417 | 0.9865 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3
- Downloads last month
- 2
Model tree for donskerclass/bert-finetuned-ner
Base model
google-bert/bert-base-casedDataset used to train donskerclass/bert-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.934
- Recall on conll2003validation set self-reported0.950
- F1 on conll2003validation set self-reported0.942
- Accuracy on conll2003validation set self-reported0.987
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="donskerclass/bert-finetuned-ner")