nllb-200-distilled-600M-dz-to-en
This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7727
- Bleu: 42.8708
- Gen Len: 13.335
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.9294 | 1.0 | 1688 | 0.8364 | 39.0175 | 13.2637 |
| 0.7929 | 2.0 | 3376 | 0.7893 | 40.9994 | 13.303 |
| 0.7069 | 3.0 | 5064 | 0.7737 | 42.4125 | 13.292 |
| 0.6482 | 4.0 | 6752 | 0.7701 | 42.826 | 13.3287 |
| 0.6231 | 5.0 | 8440 | 0.7727 | 42.8708 | 13.335 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Downloads last month
- 83
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.