<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Plant-gob-roberta-base-bne-capitel-ner
This model is a fine-tuned version of BSC-LT/roberta-base-bne-capitel-ner on the conll2002 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1071
- Precision: 0.8628
- Recall: 0.8826
- F1: 0.8726
- Accuracy: 0.9785
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: 16
- eval_batch_size: 16
- 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 |
---|---|---|---|---|---|---|---|
0.0681 | 1.0 | 521 | 0.0818 | 0.8645 | 0.8842 | 0.8742 | 0.9789 |
0.0313 | 2.0 | 1042 | 0.0841 | 0.8516 | 0.8768 | 0.8640 | 0.9779 |
0.0179 | 3.0 | 1563 | 0.0979 | 0.8584 | 0.8773 | 0.8677 | 0.9781 |
0.0091 | 4.0 | 2084 | 0.0996 | 0.8600 | 0.8819 | 0.8708 | 0.9784 |
0.0068 | 5.0 | 2605 | 0.1071 | 0.8628 | 0.8826 | 0.8726 | 0.9785 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3