punjabi-distilbert-ner
This model is a fine-tuned version of distilbert-base-multilingual-cased on an punjabi-ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0787
- Precision: 0.7618
- Recall: 0.7452
- F1: 0.7534
- Accuracy: 0.9777
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: 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 |
---|---|---|---|---|---|---|---|
0.0743 | 1.0 | 807 | 0.0794 | 0.6756 | 0.7653 | 0.7176 | 0.9731 |
0.0463 | 2.0 | 1614 | 0.0752 | 0.7545 | 0.7437 | 0.7491 | 0.9772 |
0.0371 | 3.0 | 2421 | 0.0787 | 0.7618 | 0.7452 | 0.7534 | 0.9777 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 8
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.