bert-finetuned-ner
This model is a fine-tuned version of bert-base-cased on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2964
- Precision: 0.5422
- Recall: 0.3809
- F1: 0.4475
- Accuracy: 0.9476
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 |
---|---|---|---|---|---|---|---|
No log | 1.0 | 425 | 0.2617 | 0.5380 | 0.3086 | 0.3922 | 0.9427 |
0.1895 | 2.0 | 850 | 0.2944 | 0.5930 | 0.3160 | 0.4123 | 0.9443 |
0.0702 | 3.0 | 1275 | 0.2964 | 0.5422 | 0.3809 | 0.4475 | 0.9476 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 0
Finetuned from
Dataset used to train Norika/bert-finetuned-ner
Evaluation results
- Precision on wnut_17test set self-reported0.542
- Recall on wnut_17test set self-reported0.381
- F1 on wnut_17test set self-reported0.447
- Accuracy on wnut_17test set self-reported0.948