ind-to-bbc-nmt-v2
This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the nusatranslation_mt dataset. It achieves the following results on the evaluation set:
- Loss: 1.1713
- Sacrebleu: 31.5851
- Gen Len: 45.311
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu | Gen Len |
|---|---|---|---|---|---|
| 3.6041 | 1.0 | 825 | 1.4552 | 28.698 | 45.0965 |
| 1.3318 | 2.0 | 1650 | 1.2516 | 30.4316 | 45.683 |
| 1.103 | 3.0 | 2475 | 1.1934 | 30.9199 | 45.474 |
| 0.9875 | 4.0 | 3300 | 1.1762 | 31.635 | 45.254 |
| 0.9204 | 5.0 | 4125 | 1.1713 | 31.5851 | 45.311 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.14.6
- Tokenizers 0.19.1
- Downloads last month
- 11
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for kepinsam/ind-to-bbc-nmt-v2
Base model
facebook/nllb-200-distilled-600MEvaluation results
- Sacrebleu on nusatranslation_mttest set self-reported31.585