XLMR-ENIS-finetuned-ner
This model is a fine-tuned version of vesteinn/XLMR-ENIS on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0671
- Precision: 0.9398
- Recall: 0.9518
- F1: 0.9458
- Accuracy: 0.9854
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2825 | 1.0 | 878 | 0.0712 | 0.9220 | 0.9379 | 0.9299 | 0.9815 |
| 0.0688 | 2.0 | 1756 | 0.0689 | 0.9354 | 0.9477 | 0.9415 | 0.9839 |
| 0.039 | 3.0 | 2634 | 0.0671 | 0.9398 | 0.9518 | 0.9458 | 0.9854 |
Framework versions
- Transformers 4.10.3
- Pytorch 1.9.0+cu102
- Datasets 1.12.1
- Tokenizers 0.10.3
- Downloads last month
- 21
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for vesteinn/XLMR-ENIS-finetuned-ner
Base model
vesteinn/XLMR-ENISDataset used to train vesteinn/XLMR-ENIS-finetuned-ner
Evaluation results
- Precision on conll2003self-reported0.940
- Recall on conll2003self-reported0.952
- F1 on conll2003self-reported0.946
- Accuracy on conll2003self-reported0.985