<!-- 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. -->
hindi-roberta-ner
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0251
- Precision: 0.9030
- Recall: 0.9427
- F1: 0.9224
- Accuracy: 0.9941
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: 1e-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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3913 | 1.0 | 882 | 0.0832 | 0.7304 | 0.8048 | 0.7658 | 0.9785 |
| 0.0642 | 2.0 | 1764 | 0.0370 | 0.8679 | 0.9023 | 0.8847 | 0.9903 |
| 0.0331 | 3.0 | 2646 | 0.0251 | 0.9030 | 0.9427 | 0.9224 | 0.9941 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
