<!-- 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-ecolindo
This model was trained from scratch on the EColIndo dataset. It achieves the following results on the evaluation set:
- Loss: 0.8704
- Bleu: 37.2396
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 4000
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu |
---|---|---|---|---|
1.3017 | 1.0 | 21019 | 0.9831 | 35.0676 |
1.0088 | 2.0 | 42038 | 0.9318 | 36.3191 |
0.9472 | 3.0 | 63057 | 0.9090 | 36.5221 |
0.9078 | 4.0 | 84076 | 0.8919 | 36.3949 |
0.8789 | 5.0 | 105095 | 0.8833 | 37.3689 |
0.8576 | 6.0 | 126114 | 0.8785 | 37.2262 |
0.8403 | 7.0 | 147133 | 0.8748 | 37.2933 |
0.8281 | 8.0 | 168152 | 0.8717 | 37.2952 |
0.8186 | 9.0 | 189171 | 0.8709 | 37.2801 |
0.813 | 10.0 | 210190 | 0.8704 | 37.2396 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.0
- Datasets 2.10.1
- Tokenizers 0.11.0