multilingual-cased-finetuned-luganda-qa
This model is a fine-tuned version of badokorach/multilingual-cased-finetuned-luganda on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.015 | 1.0 | 2215 | 0.0140 |
| 0.0103 | 2.0 | 4430 | 0.0057 |
| 0.0128 | 3.0 | 6645 | 0.0003 |
| 0.0085 | 4.0 | 8860 | 0.0004 |
| 0.0104 | 5.0 | 11075 | 0.0051 |
| 0.0083 | 6.0 | 13290 | 0.0020 |
| 0.0074 | 7.0 | 15505 | 0.0025 |
| 0.0056 | 8.0 | 17720 | 0.0000 |
| 0.0023 | 9.0 | 19935 | 0.0001 |
| 0.0032 | 10.0 | 22150 | 0.0000 |
| 0.0007 | 11.0 | 24365 | 0.0000 |
| 0.0003 | 12.0 | 26580 | 0.0000 |
| 0.0017 | 13.0 | 28795 | 0.0000 |
| 0.0005 | 14.0 | 31010 | 0.0000 |
| 0.0002 | 15.0 | 33225 | 0.0000 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3