metadata
license: cc-by-nc-4.0
base_model: facebook/nllb-200-distilled-600M
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: NLLB_Egyptian_to_English256
results: []
NLLB_Egyptian_to_English256
This model is a fine-tuned version of facebook/nllb-200-distilled-600M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4083
- Bleu: 18.8886
- Gen Len: 20.2415
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: 0.0003
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.5237 | 1.0 | 6248 | 2.2856 | 16.2331 | 20.3176 |
| 0.7885 | 2.0 | 12496 | 2.2266 | 17.554 | 20.3609 |
| 0.3508 | 3.0 | 18744 | 2.4083 | 18.8886 | 20.2415 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2