RoBerta-finetuned-ner
This Name Entity Recognition model is a fine-tuned version of FacebookAI/roberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0605
- Precision: 0.9502
- Recall: 0.9605
- F1: 0.9553
- Accuracy: 0.9898
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 |
|---|---|---|---|---|---|---|---|
| 0.0248 | 1.0 | 1756 | 0.0636 | 0.9474 | 0.9547 | 0.9510 | 0.9885 |
| 0.014 | 2.0 | 3512 | 0.0734 | 0.9483 | 0.9578 | 0.9530 | 0.9886 |
| 0.0124 | 3.0 | 5268 | 0.0605 | 0.9502 | 0.9605 | 0.9553 | 0.9898 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 143
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for heisenberg3376/roberta-base-finetuned-ner
Base model
FacebookAI/roberta-baseDataset used to train heisenberg3376/roberta-base-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.950
- Recall on conll2003validation set self-reported0.960
- F1 on conll2003validation set self-reported0.955
- Accuracy on conll2003validation set self-reported0.990