RoBERTa_conll_epoch_7
This model is a fine-tuned version of distilroberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0772
- Precision: 0.9447
- Recall: 0.9569
- F1: 0.9508
- Accuracy: 0.9886
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: 5e-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: 7
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.078 | 1.0 | 1756 | 0.0745 | 0.9048 | 0.9310 | 0.9177 | 0.9831 |
0.0424 | 2.0 | 3512 | 0.0702 | 0.9317 | 0.9451 | 0.9383 | 0.9851 |
0.0254 | 3.0 | 5268 | 0.0722 | 0.9312 | 0.9498 | 0.9404 | 0.9857 |
0.0173 | 4.0 | 7024 | 0.0678 | 0.9348 | 0.9505 | 0.9426 | 0.9867 |
0.0086 | 5.0 | 8780 | 0.0798 | 0.9306 | 0.9498 | 0.9401 | 0.9859 |
0.0058 | 6.0 | 10536 | 0.0786 | 0.9406 | 0.9562 | 0.9483 | 0.9881 |
0.0033 | 7.0 | 12292 | 0.0772 | 0.9447 | 0.9569 | 0.9508 | 0.9886 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 1
Finetuned from
Dataset used to train ICT2214Team7/RoBERTa_conll_epoch_7
Evaluation results
- Precision on conll2003validation set self-reported0.945
- Recall on conll2003validation set self-reported0.957
- F1 on conll2003validation set self-reported0.951
- Accuracy on conll2003validation set self-reported0.989