bert-finetuned-ner-aug-v1
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: 0.0989
- Precision: 0.8647
- Recall: 0.8894
- F1: 0.8769
- Accuracy: 0.9717
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
- training_steps: 1755
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.153 | 1.0 | 1755 | 0.0989 | 0.8647 | 0.8894 | 0.8769 | 0.9717 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 97
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for mbalos/bert-finetuned-ner-aug-v1
Base model
google-bert/bert-base-casedDataset used to train mbalos/bert-finetuned-ner-aug-v1
Evaluation results
- Precision on conll2003validation set self-reported0.865
- Recall on conll2003validation set self-reported0.889
- F1 on conll2003validation set self-reported0.877
- Accuracy on conll2003validation set self-reported0.972