RoBERTa_conll_epoch_4
This model is a fine-tuned version of distilroberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0595
- Precision: 0.9446
- Recall: 0.9586
- F1: 0.9516
- Accuracy: 0.9885
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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0785 | 1.0 | 1756 | 0.0667 | 0.9131 | 0.9335 | 0.9232 | 0.9835 |
0.0379 | 2.0 | 3512 | 0.0619 | 0.9341 | 0.9445 | 0.9392 | 0.9864 |
0.0207 | 3.0 | 5268 | 0.0609 | 0.9424 | 0.9529 | 0.9476 | 0.9872 |
0.0105 | 4.0 | 7024 | 0.0595 | 0.9446 | 0.9586 | 0.9516 | 0.9885 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
Finetuned from
Dataset used to train ICT2214Team7/RoBERTa_conll_epoch_4
Evaluation results
- Precision on conll2003validation set self-reported0.945
- Recall on conll2003validation set self-reported0.959
- F1 on conll2003validation set self-reported0.952
- Accuracy on conll2003validation set self-reported0.988