bert-base-uncased-conll2003
This model is a fine-tuned version of bert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1530
- Precision: 0.8885
- Recall: 0.9046
- F1: 0.8965
- Accuracy: 0.9781
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0651 | 1.0 | 3922 | 0.1483 | 0.8842 | 0.9067 | 0.8953 | 0.9775 |
| 0.0287 | 2.0 | 7844 | 0.1530 | 0.8885 | 0.9046 | 0.8965 | 0.9781 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.2.2
- Datasets 2.20.0
- Tokenizers 0.13.3
- Downloads last month
- 56
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for joshuaphua/bert-base-uncased-conll2003
Base model
google-bert/bert-base-uncasedDataset used to train joshuaphua/bert-base-uncased-conll2003
Evaluation results
- Precision on conll2003test set self-reported0.889
- Recall on conll2003test set self-reported0.905
- F1 on conll2003test set self-reported0.896
- Accuracy on conll2003test set self-reported0.978