distilbert-base-cased-finetuned-CONLL2003
This model is a fine-tuned version of distilbert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0983
- Precision: 0.9276
- Recall: 0.9470
- F1: 0.9372
- Accuracy: 0.9848
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0302 | 1.0 | 1756 | 0.0832 | 0.9055 | 0.9318 | 0.9185 | 0.9812 |
0.024 | 2.0 | 3512 | 0.0867 | 0.9237 | 0.9387 | 0.9311 | 0.9833 |
0.0123 | 3.0 | 5268 | 0.0909 | 0.9224 | 0.9438 | 0.9330 | 0.9845 |
0.0059 | 4.0 | 7024 | 0.0962 | 0.9218 | 0.9448 | 0.9332 | 0.9844 |
0.0026 | 5.0 | 8780 | 0.0983 | 0.9276 | 0.9470 | 0.9372 | 0.9848 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 3
Dataset used to train EulerianKnight/distilbert-base-cased-finetuned-CONLL2003
Evaluation results
- Precision on conll2003validation set self-reported0.928
- Recall on conll2003validation set self-reported0.947
- F1 on conll2003validation set self-reported0.937
- Accuracy on conll2003validation set self-reported0.985