metadata
license: cc-by-nc-4.0
base_model: facebook/nllb-200-distilled-600M
tags:
- generated_from_trainer
datasets:
- nusatranslation_mt
metrics:
- sacrebleu
model-index:
- name: indonesian_to_bataknese_translation_model
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: nusatranslation_mt
type: nusatranslation_mt
config: nusatranslation_mt_btk_ind_source
split: test
args: nusatranslation_mt_btk_ind_source
metrics:
- name: Sacrebleu
type: sacrebleu
value: 31.8044
indonesian_to_bataknese_translation_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: 1.1474
- Sacrebleu: 31.8044
- Gen Len: 45.2525
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: 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 |
|---|---|---|---|---|---|
| 1.6014 | 1.0 | 1650 | 1.3826 | 29.3368 | 45.439 |
| 1.2189 | 2.0 | 3300 | 1.2135 | 31.2236 | 45.2075 |
| 1.0274 | 3.0 | 4950 | 1.1556 | 30.8443 | 45.661 |
| 0.8923 | 4.0 | 6600 | 1.1471 | 31.6079 | 45.1555 |
| 0.8094 | 5.0 | 8250 | 1.1474 | 31.8044 | 45.2525 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.13.1
- Tokenizers 0.14.1