metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-ko-en
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: opus-mt-ko-en
results: []
opus-mt-ko-en
This model is a fine-tuned version of Helsinki-NLP/opus-mt-ko-en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7378
- Bleu: 41.6212
- Gen Len: 10.3771
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.8027 | 1.0 | 16549 | 0.8758 | 36.6942 | 10.397 |
| 0.6598 | 2.0 | 33098 | 0.7735 | 40.1498 | 10.369 |
| 0.6019 | 3.0 | 49647 | 0.7378 | 41.6212 | 10.3771 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0