metadata
library_name: transformers
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-mul-en
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: my_yoruba_translator_new1
results: []
my_yoruba_translator_new1
This model is a fine-tuned version of Helsinki-NLP/opus-mt-mul-en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4760
- Bleu: 19.1364
- Gen Len: 24.5459
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 252 | 2.6553 | 17.4458 | 25.2511 |
| 2.9795 | 2.0 | 504 | 2.5441 | 18.4384 | 26.4764 |
| 2.9795 | 3.0 | 756 | 2.5060 | 18.9805 | 24.5285 |
| 2.3359 | 4.0 | 1008 | 2.4875 | 19.0552 | 25.3161 |
| 2.3359 | 5.0 | 1260 | 2.4766 | 19.2483 | 25.4734 |
| 2.1524 | 6.0 | 1512 | 2.4760 | 19.1364 | 24.5459 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3