metadata
license: apache-2.0
base_model: google/muril-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: punjabi-muril-ner
results: []
punjabi-muril-ner
This model is a fine-tuned version of google/muril-base-cased on an punjabi-ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0654
- Precision: 0.7923
- Recall: 0.8113
- F1: 0.8017
- Accuracy: 0.9859
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3366 | 1.0 | 1613 | 0.2698 | 0.0 | 0.0 | 0.0 | 0.9551 |
| 0.1552 | 2.0 | 3226 | 0.1180 | 0.7114 | 0.4972 | 0.5853 | 0.9763 |
| 0.0959 | 3.0 | 4839 | 0.0904 | 0.7262 | 0.7161 | 0.7211 | 0.9829 |
| 0.0708 | 4.0 | 6452 | 0.0751 | 0.7679 | 0.7498 | 0.7587 | 0.9840 |
| 0.0474 | 5.0 | 8065 | 0.0672 | 0.7907 | 0.7731 | 0.7818 | 0.9854 |
| 0.0367 | 6.0 | 9678 | 0.0627 | 0.7870 | 0.8045 | 0.7957 | 0.9856 |
| 0.0308 | 7.0 | 11291 | 0.0598 | 0.7942 | 0.7915 | 0.7928 | 0.9859 |
| 0.0247 | 8.0 | 12904 | 0.0612 | 0.7891 | 0.8123 | 0.8005 | 0.9860 |
| 0.0202 | 9.0 | 14517 | 0.0666 | 0.8015 | 0.8015 | 0.8015 | 0.9860 |
| 0.0181 | 10.0 | 16130 | 0.0654 | 0.7923 | 0.8113 | 0.8017 | 0.9859 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1