bert-large-20-ner
This model is a fine-tuned version of bert-large-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5525
- Precision: 0.2643
- Recall: 0.0530
- F1: 0.0883
- Accuracy: 0.8491
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 25 | 0.7702 | 0.2857 | 0.0003 | 0.0007 | 0.8326 |
| No log | 2.0 | 50 | 0.6046 | 0.1537 | 0.0106 | 0.0198 | 0.8373 |
| No log | 3.0 | 75 | 0.5525 | 0.2643 | 0.0530 | 0.0883 | 0.8491 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1