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 unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0831
- Precision: 0.7350
- Recall: 0.7591
- F1: 0.7469
- Accuracy: 0.9843
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3465 | 1.0 | 1613 | 0.2747 | 0.0 | 0.0 | 0.0 | 0.9551 |
| 0.1642 | 2.0 | 3226 | 0.1273 | 0.6436 | 0.5216 | 0.5762 | 0.9758 |
| 0.1053 | 3.0 | 4839 | 0.0986 | 0.7257 | 0.7156 | 0.7206 | 0.9824 |
| 0.0863 | 4.0 | 6452 | 0.0854 | 0.7166 | 0.7620 | 0.7386 | 0.9837 |
| 0.0705 | 5.0 | 8065 | 0.0831 | 0.7350 | 0.7591 | 0.7469 | 0.9843 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.13.3