|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: facebook/nllb-200-distilled-600M |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: nllb-200-distilled-600M-finetuned-ar-to-en |
|
results: [] |
|
pipeline_tag: translation |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# nllb-200-distilled-600M-finetuned-ar-to-en |
|
|
|
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7281 |
|
- Bleu: 63.3172 |
|
- Gen Len: 65.7 |
|
|
|
## 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 | Bleu | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:| |
|
| 1.4803 | 1.0 | 695 | 0.9925 | 48.0036 | 68.092 | |
|
| 1.0588 | 2.0 | 1390 | 0.8618 | 53.6714 | 67.794 | |
|
| 0.8397 | 3.0 | 2085 | 0.8034 | 56.8749 | 67.316 | |
|
| 0.7816 | 4.0 | 2780 | 0.7718 | 59.7588 | 65.822 | |
|
| 0.7349 | 5.0 | 3475 | 0.7509 | 60.9155 | 66.205 | |
|
| 0.6737 | 6.0 | 4170 | 0.7422 | 61.9048 | 65.348 | |
|
| 0.6373 | 7.0 | 4865 | 0.7338 | 62.8549 | 65.607 | |
|
| 0.617 | 8.0 | 5560 | 0.7308 | 63.6105 | 65.335 | |
|
| 0.6068 | 9.0 | 6255 | 0.7276 | 63.452 | 65.594 | |
|
| 0.5913 | 10.0 | 6950 | 0.7281 | 63.3172 | 65.7 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 1.13.1 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
