bert-base-cased_conll2003-CRF-first-ner
This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0546
- Precision: 0.6483
- Recall: 0.3940
- F1: 0.4902
- Accuracy: 0.9225
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.089 | 1.0 | 7021 | 0.0522 | 0.6315 | 0.3781 | 0.4730 | 0.9193 |
0.0203 | 2.0 | 14042 | 0.0481 | 0.6587 | 0.4044 | 0.5011 | 0.9233 |
0.0166 | 3.0 | 21063 | 0.0546 | 0.6483 | 0.3940 | 0.4902 | 0.9225 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.2+cu102
- Datasets 2.2.2
- Tokenizers 0.12.1
- Downloads last month
- 8
Unable to determine this model’s pipeline type. Check the
docs
.