opus-mt-th-en-finetuned-en-to-th
This model is a fine-tuned version of Helsinki-NLP/opus-mt-th-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7468
- Bleu: 0.4565
- Gen Len: 112.35
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
2.6696 | 6.25 | 500 | 2.5634 | 0.1874 | 122.75 |
1.6018 | 12.5 | 1000 | 2.6129 | 0.4756 | 115.55 |
1.1813 | 18.75 | 1500 | 2.7468 | 0.4565 | 112.35 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 0