RoBERTa_conll_epoch_5
This model is a fine-tuned version of distilroberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0716
- Precision: 0.9370
- Recall: 0.9539
- F1: 0.9454
- Accuracy: 0.9873
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0787 | 1.0 | 1756 | 0.0734 | 0.9024 | 0.9317 | 0.9168 | 0.9819 |
0.0389 | 2.0 | 3512 | 0.0706 | 0.9359 | 0.9440 | 0.9399 | 0.9854 |
0.023 | 3.0 | 5268 | 0.0632 | 0.9340 | 0.9483 | 0.9411 | 0.9864 |
0.0137 | 4.0 | 7024 | 0.0762 | 0.9368 | 0.9534 | 0.9450 | 0.9875 |
0.0054 | 5.0 | 8780 | 0.0716 | 0.9370 | 0.9539 | 0.9454 | 0.9873 |
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_5
Evaluation results
- Precision on conll2003validation set self-reported0.937
- Recall on conll2003validation set self-reported0.954
- F1 on conll2003validation set self-reported0.945
- Accuracy on conll2003validation set self-reported0.987