metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: urdu-bert-ner
results: []
urdu-bert-ner
This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2125
- Precision: 0.8073
- Recall: 0.8272
- F1: 0.8171
- Accuracy: 0.9592
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 |
|---|---|---|---|---|---|---|---|
| 0.1593 | 1.0 | 2272 | 0.1469 | 0.7158 | 0.8005 | 0.7558 | 0.9468 |
| 0.1154 | 2.0 | 4544 | 0.1304 | 0.7720 | 0.8116 | 0.7913 | 0.9547 |
| 0.0862 | 3.0 | 6816 | 0.1381 | 0.7912 | 0.8117 | 0.8013 | 0.9557 |
| 0.0673 | 4.0 | 9088 | 0.1404 | 0.8006 | 0.8099 | 0.8052 | 0.9567 |
| 0.0515 | 5.0 | 11360 | 0.1511 | 0.8135 | 0.8063 | 0.8099 | 0.9578 |
| 0.0402 | 6.0 | 13632 | 0.1666 | 0.8030 | 0.8235 | 0.8131 | 0.9582 |
| 0.0286 | 7.0 | 15904 | 0.1848 | 0.8066 | 0.8208 | 0.8137 | 0.9579 |
| 0.022 | 8.0 | 18176 | 0.1957 | 0.8060 | 0.8226 | 0.8142 | 0.9585 |
| 0.0201 | 9.0 | 20448 | 0.2062 | 0.8022 | 0.8283 | 0.8151 | 0.9585 |
| 0.0164 | 10.0 | 22720 | 0.2125 | 0.8073 | 0.8272 | 0.8171 | 0.9592 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.13.3