bert-finetuned-ner-90percent
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5444
- Precision: 0.8236
- Recall: 0.8483
- F1: 0.8358
- Accuracy: 0.9263
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: 2022
- 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 | 68 | 0.4938 | 0.8223 | 0.8544 | 0.8380 | 0.9284 |
| No log | 2.0 | 136 | 0.5465 | 0.8265 | 0.8514 | 0.8388 | 0.9256 |
| No log | 3.0 | 204 | 0.5444 | 0.8236 | 0.8483 | 0.8358 | 0.9263 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2