xlm-roberta-base-esg-ner
This model is a fine-tuned version of xlm-roberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3380
- Precision: 0.5073
- Recall: 0.4847
- F1: 0.4957
- Accuracy: 0.8927
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: 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4859 | 1.0 | 1756 | 0.3975 | 0.4732 | 0.4137 | 0.4415 | 0.8766 |
| 0.331 | 2.0 | 3512 | 0.3380 | 0.5073 | 0.4847 | 0.4957 | 0.8927 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1