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: 0.9264
- Recall: 0.9372
- F1: 0.9318
- Accuracy: 0.9835
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 |
---|---|---|---|---|---|---|---|
0.2565 | 1.0 | 878 | 0.0714 | 0.9014 | 0.9214 | 0.9113 | 0.9797 |
0.0503 | 2.0 | 1756 | 0.0622 | 0.9248 | 0.9309 | 0.9278 | 0.9828 |
0.0312 | 3.0 | 2634 | 0.0611 | 0.9264 | 0.9372 | 0.9318 | 0.9835 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 0
Finetuned from
Dataset used to train ckandemir/distilbert-base-uncased-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.926
- Recall on conll2003validation set self-reported0.937
- F1 on conll2003validation set self-reported0.932
- Accuracy on conll2003validation set self-reported0.983