# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("greatakela/bert-base-cased")
model = AutoModelForTokenClassification.from_pretrained("greatakela/bert-base-cased")Quick Links
bert-base-cased
This model was trained from scratch on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0646
- Precision: 0.9352
- Recall: 0.9500
- F1: 0.9426
- Accuracy: 0.9859
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 |
|---|---|---|---|---|---|---|---|
| 0.0771 | 1.0 | 1756 | 0.0778 | 0.9094 | 0.9323 | 0.9207 | 0.9792 |
| 0.0406 | 2.0 | 3512 | 0.0575 | 0.9314 | 0.9502 | 0.9407 | 0.9860 |
| 0.0226 | 3.0 | 5268 | 0.0646 | 0.9352 | 0.9500 | 0.9426 | 0.9859 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 4
Dataset used to train greatakela/bert-base-cased
Evaluation results
- Precision on conll2003validation set self-reported0.935
- Recall on conll2003validation set self-reported0.950
- F1 on conll2003validation set self-reported0.943
- Accuracy on conll2003validation set self-reported0.986
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="greatakela/bert-base-cased")