metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: ner_bert_urdu
results: []
ner_bert_urdu
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: 0.0104
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: 32
- eval_batch_size: 64
- 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 |
|---|---|---|---|
| 0.0035 | 1.0 | 1314 | 0.0083 |
| 0.0032 | 2.0 | 2628 | 0.0084 |
| 0.0031 | 3.0 | 3942 | 0.0063 |
| 0.0036 | 4.0 | 5256 | 0.0070 |
| 0.0034 | 5.0 | 6570 | 0.0077 |
| 0.0033 | 6.0 | 7884 | 0.0086 |
| 0.0029 | 7.0 | 9198 | 0.0085 |
| 0.0028 | 8.0 | 10512 | 0.0101 |
| 0.0027 | 9.0 | 11826 | 0.0098 |
| 0.0024 | 10.0 | 13140 | 0.0104 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3