distilbert-base-uncased-finetuned-ner
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0611
- Precision: 0.9272
- Recall: 0.9382
- F1: 0.9327
- Accuracy: 0.9843
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: 16
- eval_batch_size: 16
- 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 |
---|---|---|---|---|---|---|---|
0.2432 | 1.0 | 878 | 0.0689 | 0.9132 | 0.9203 | 0.9168 | 0.9813 |
0.0507 | 2.0 | 1756 | 0.0608 | 0.9208 | 0.9346 | 0.9276 | 0.9835 |
0.03 | 3.0 | 2634 | 0.0611 | 0.9272 | 0.9382 | 0.9327 | 0.9843 |
Framework versions
- Transformers 4.9.1
- Pytorch 1.9.0+cu102
- Datasets 1.10.2
- Tokenizers 0.10.3
- Downloads last month
- 22
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.