metadata
license: apache-2.0
base_model: google/muril-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: urdu-muril-ner
results: []
urdu-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: 0.1489
- Precision: 0.7802
- Recall: 0.8229
- F1: 0.8009
- Accuracy: 0.9570
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 |
|---|---|---|---|---|---|---|---|
| 0.3946 | 1.0 | 2272 | 0.3188 | 0.7387 | 0.6442 | 0.6882 | 0.9350 |
| 0.2026 | 2.0 | 4544 | 0.1960 | 0.7728 | 0.7797 | 0.7762 | 0.9535 |
| 0.141 | 3.0 | 6816 | 0.1554 | 0.7735 | 0.8139 | 0.7932 | 0.9557 |
| 0.1038 | 4.0 | 9088 | 0.1474 | 0.7836 | 0.8163 | 0.7996 | 0.9568 |
| 0.0889 | 5.0 | 11360 | 0.1489 | 0.7802 | 0.8229 | 0.8009 | 0.9570 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1