Token Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("Arron/bert-finetuned-ner")
model = AutoModelForTokenClassification.from_pretrained("Arron/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: 0.0607
- Precision: 0.9319
- Recall: 0.9495
- F1: 0.9406
- Accuracy: 0.9860
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 |
|---|---|---|---|---|---|---|---|
| 0.0845 | 1.0 | 1756 | 0.0626 | 0.9146 | 0.9337 | 0.9241 | 0.9827 |
| 0.0414 | 2.0 | 3512 | 0.0561 | 0.9321 | 0.9492 | 0.9405 | 0.9861 |
| 0.0198 | 3.0 | 5268 | 0.0607 | 0.9319 | 0.9495 | 0.9406 | 0.9860 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 5
Dataset used to train Arron/bert-finetuned-ner
Evaluation results
- Precision on conll2003self-reported0.932
- Recall on conll2003self-reported0.950
- F1 on conll2003self-reported0.941
- Accuracy on conll2003self-reported0.986
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Arron/bert-finetuned-ner")