<!-- 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. -->
bataknese_to_indonesian_translation_t5_model
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: 0.5545
- Sacrebleu: 39.6897
- Gen Len: 39.0195
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: 8e-05
- train_batch_size: 4
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu | Gen Len |
|---|---|---|---|---|---|
| 0.6241 | 1.0 | 1650 | 0.5763 | 36.5999 | 39.4 |
| 0.4831 | 2.0 | 3300 | 0.5331 | 38.7447 | 38.766 |
| 0.3915 | 3.0 | 4950 | 0.5305 | 39.571 | 39.359 |
| 0.3017 | 4.0 | 6600 | 0.5404 | 39.9148 | 39.211 |
| 0.2542 | 5.0 | 8250 | 0.5545 | 39.6897 | 39.0195 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
