Nso-En_update
This model is a fine-tuned version of kabelomalapane/En-Nso on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9219
- Bleu: 0.0
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 | Bleu |
|---|---|---|---|---|
| No log | 1.0 | 108 | 2.0785 | 0.0 |
| No log | 2.0 | 216 | 1.9015 | 0.0 |
| No log | 3.0 | 324 | 1.8730 | 0.0 |
| No log | 4.0 | 432 | 1.8626 | 0.0 |
| 2.1461 | 5.0 | 540 | 1.8743 | 0.0 |
| 2.1461 | 6.0 | 648 | 1.8903 | 0.0 |
| 2.1461 | 7.0 | 756 | 1.9018 | 0.0 |
| 2.1461 | 8.0 | 864 | 1.9236 | 0.0 |
| 2.1461 | 9.0 | 972 | 1.9210 | 0.0 |
| 1.2781 | 10.0 | 1080 | 1.9219 | 0.0 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1