bert-large-ner-wnut-17
This model is a fine-tuned version of bert-large-uncased on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2851
- Precision: 0.6240
- Recall: 0.4245
- F1: 0.5052
- Accuracy: 0.9504
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: 5e-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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 213 | 0.2551 | 0.6727 | 0.3105 | 0.4249 | 0.9446 |
| No log | 2.0 | 426 | 0.2521 | 0.6491 | 0.4235 | 0.5126 | 0.9510 |
| 0.1128 | 3.0 | 639 | 0.2851 | 0.6240 | 0.4245 | 0.5052 | 0.9504 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2