Token Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("ish97/bert-finetuned-chunking")
model = AutoModelForTokenClassification.from_pretrained("ish97/bert-finetuned-chunking")Quick Links
bert-finetuned-chunking
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: 0.1594
- Precision: 0.9230
- Recall: 0.9218
- F1: 0.9224
- Accuracy: 0.9619
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 |
|---|---|---|---|---|---|---|---|
| 0.1887 | 1.0 | 1756 | 0.1793 | 0.9167 | 0.9112 | 0.9139 | 0.9573 |
| 0.128 | 2.0 | 3512 | 0.1552 | 0.9228 | 0.9187 | 0.9207 | 0.9609 |
| 0.091 | 3.0 | 5268 | 0.1594 | 0.9230 | 0.9218 | 0.9224 | 0.9619 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 6
Dataset used to train ish97/bert-finetuned-chunking
Evaluation results
- Precision on conll2003self-reported0.923
- Recall on conll2003self-reported0.922
- F1 on conll2003self-reported0.922
- Accuracy on conll2003self-reported0.962
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="ish97/bert-finetuned-chunking")