bert-finetuned-ner
This model is a fine-tuned version of rishika-v/bert-finetuned-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1980
- Precision: 0.6607
- Recall: 0.5583
- F1: 0.6052
- Accuracy: 0.9460
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 |
---|---|---|---|---|---|---|---|
0.1972 | 1.0 | 14000 | 0.1650 | 0.6842 | 0.5005 | 0.5781 | 0.9434 |
0.1751 | 2.0 | 28000 | 0.1729 | 0.6795 | 0.5562 | 0.6117 | 0.9470 |
0.1816 | 3.0 | 42000 | 0.1980 | 0.6607 | 0.5583 | 0.6052 | 0.9460 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2