<!-- 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. -->
urdu-distilbert-ner
This model is a fine-tuned version of distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1387
- Precision: 0.7575
- Recall: 0.8057
- F1: 0.7809
- Accuracy: 0.9535
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1637 | 1.0 | 2272 | 0.1505 | 0.7131 | 0.7800 | 0.7451 | 0.9457 |
| 0.1159 | 2.0 | 4544 | 0.1390 | 0.7377 | 0.8037 | 0.7693 | 0.9507 |
| 0.0882 | 3.0 | 6816 | 0.1387 | 0.7575 | 0.8057 | 0.7809 | 0.9535 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.13.3
