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: 0.0590
- Precision: 0.9266
- Recall: 0.9381
- F1: 0.9323
- Accuracy: 0.9844
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 |
---|---|---|---|---|---|---|---|
0.0616 | 1.0 | 878 | 0.0604 | 0.9195 | 0.9370 | 0.9282 | 0.9833 |
0.0328 | 2.0 | 1756 | 0.0588 | 0.9258 | 0.9375 | 0.9316 | 0.9841 |
0.0246 | 3.0 | 2634 | 0.0590 | 0.9266 | 0.9381 | 0.9323 | 0.9844 |
Framework versions
- Transformers 4.8.2
- Pytorch 1.8.1
- Datasets 1.9.0
- Tokenizers 0.10.3
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.