This model is a fine-tuned version of bert-large-uncased-whole-word-masking on the conll2003 dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4071 | 1.0 | 877 | 0.0584 | 0.9306 | 0.9418 | 0.9362 | 0.9851 |
| 0.0482 | 2.0 | 1754 | 0.0594 | 0.9362 | 0.9491 | 0.9426 | 0.9863 |
| 0.0217 | 3.0 | 2631 | 0.0550 | 0.9479 | 0.9584 | 0.9531 | 0.9885 |
| 0.0103 | 4.0 | 3508 | 0.0592 | 0.9527 | 0.9569 | 0.9548 | 0.9887 |
pytorch_model.bin 1.3 GBtraining_args.bin 2.8 kB