RoBERTa_conll_learning_rate1e4
This model is a fine-tuned version of distilroberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0665
- Precision: 0.9345
- Recall: 0.9463
- F1: 0.9404
- Accuracy: 0.9863
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: 0.0001
- 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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0909 | 1.0 | 1756 | 0.0778 | 0.8810 | 0.9130 | 0.8967 | 0.9786 |
0.0413 | 2.0 | 3512 | 0.0720 | 0.9242 | 0.9337 | 0.9289 | 0.9838 |
0.0194 | 3.0 | 5268 | 0.0665 | 0.9345 | 0.9463 | 0.9404 | 0.9863 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 13
Model tree for ICT2214Team7/RoBERTa_conll_learning_rate1e4
Base model
distilbert/distilroberta-baseDataset used to train ICT2214Team7/RoBERTa_conll_learning_rate1e4
Evaluation results
- Precision on conll2003validation set self-reported0.935
- Recall on conll2003validation set self-reported0.946
- F1 on conll2003validation set self-reported0.940
- Accuracy on conll2003validation set self-reported0.986