<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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: 0.0605
- Precision: 0.9270
- Recall: 0.9353
- F1: 0.9312
- Accuracy: 0.9839
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 |
---|---|---|---|---|---|---|---|
0.2477 | 1.0 | 878 | 0.0701 | 0.9041 | 0.9216 | 0.9127 | 0.9802 |
0.0494 | 2.0 | 1756 | 0.0613 | 0.9258 | 0.9312 | 0.9285 | 0.9830 |
0.0305 | 3.0 | 2634 | 0.0605 | 0.9270 | 0.9353 | 0.9312 | 0.9839 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3