|
--- |
|
library_name: transformers |
|
license: cc-by-nc-4.0 |
|
base_model: facebook/nllb-200-distilled-600M |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: nllb-finetuned-de-en |
|
results: [] |
|
--- |
|
|
|
<!-- 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-finetuned-de-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: 0.5475 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 1.0 | 486 | 1.1181 | |
|
| 1.3516 | 2.0 | 972 | 0.9976 | |
|
| 1.0459 | 3.0 | 1458 | 0.9073 | |
|
| 0.9073 | 4.0 | 1944 | 0.8393 | |
|
| 0.7901 | 5.0 | 2430 | 0.7772 | |
|
| 0.7072 | 6.0 | 2916 | 0.7292 | |
|
| 0.6262 | 7.0 | 3402 | 0.6872 | |
|
| 0.5713 | 8.0 | 3888 | 0.6532 | |
|
| 0.5185 | 9.0 | 4374 | 0.6228 | |
|
| 0.48 | 10.0 | 4860 | 0.5997 | |
|
| 0.4424 | 11.0 | 5346 | 0.5795 | |
|
| 0.4242 | 12.0 | 5832 | 0.5646 | |
|
| 0.4049 | 13.0 | 6318 | 0.5558 | |
|
| 0.3822 | 14.0 | 6804 | 0.5492 | |
|
| 0.3792 | 15.0 | 7290 | 0.5475 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.5.0+cu121 |
|
- Tokenizers 0.19.1 |
|
|
